Forgot your password?
typodupeerror
Hardware Technology

"Self-Healing" NAND Flash Memory That Can Survive Over 100 Million Cycles 76

Posted by Unknown Lamer
from the forged-in-the-fires-of-mount-nand dept.
another random user writes with an interesting use of 800C heating elements to keep flash working longer. It's long been known that heating NAND to temperatures around 250C can restore life, but doing so was practically impossible. From the article: "Engineers at Macronix have a solution that moves flash memory over to a new life. ... They redesigned a flash memory chip to include onboard heaters to anneal small groups of memory cells. Applying a brief jolt of heat to a very restricted area within the chip (800 degrees C) returns the cell to a 'good' state. ... According to project member HangTing Lue, the annealing can be done infrequently and on one sector at a time while the device is inactive but still connected to the power source. It would not drain a cellphone battery, he added." It's still a long way from commercialization, but if it works on a small scale...
This discussion has been archived. No new comments can be posted.

"Self-Healing" NAND Flash Memory That Can Survive Over 100 Million Cycles

Comments Filter:
  • 800C? (Score:4, Interesting)

    by girlintraining (1395911) on Sunday December 02, 2012 @07:10PM (#42163985)

    What are the odds they'll let something that can heat up that much on an airplane, once they read this article? :\ More seriously, I assume this is over a very, very small area, and the chip dissipates that heat within a few minutes, and that it would only be warm to the touch for a few moments... but I still gotta ask: Is there the possibility of catastrophic failure? Like if the chip was maliciously reprogrammed to trigger all the heating elements simultaniously?

    • Re:800C? (Score:5, Interesting)

      by space fountain (1897346) on Sunday December 02, 2012 @07:21PM (#42164057)
      Probably not enough power.
    • Re:800C? (Score:5, Informative)

      by mfwitten (1906728) on Sunday December 02, 2012 @07:24PM (#42164073)

      As you later hint, a high temperature does not imply a great deal of heat. Also, a hardware fail-safe (i.e., a fuse) is the obvious solution to any such maliciousness.

    • Re:800C? (Score:5, Informative)

      by Anonymous Coward on Sunday December 02, 2012 @07:25PM (#42164081)

      You do realize that Incandescent light bulbs are at 3000K or so. So, they have been letting things get over 800C since the beginning of commercial airlines.

      • This. Heat is heat per area. So long its not 800C on the fucking shell, its irrelevant.

      • Re:800C? (Score:4, Insightful)

        by girlintraining (1395911) on Sunday December 02, 2012 @10:26PM (#42165155)

        You do realize that Incandescent light bulbs are at 3000K or so.

        I do. Do you realize that congress isn't exactly known for its firm grasp of science? Remember... they banned people from carrying more than a couple ounces of liquids out of fear they could be used to create binary explosives because that was the plot of a Die Hard movie, not because there was any evidence terrorists had any plans of using it, or that it would even provide the explosive force necessary. As a result, people flying home after surgery have had their ice packs confinscated, they've been forced to put diabetic pumps through metal detectors and body scanners (rendering them inoperative and posing an immediate threat to the life of the passenger), etc.

        So I posed the question to underscore the line of questioning that average person would have about such devices.... and instead I have my intelligence insulted. No matter how correct you may be, that is not an excuse for poor form.

      • Sorry, but the value 3000K refers to the color temperature of incandescent bulbs, not the actual temperature. See this chart [3drender.com].

        Did you REALLY think the filament of an ordinary incandescent tungsten bulb operates at 4940.33 degrees Fahrenheit (2727 degrees C)? Seriously?

        • Re: (Score:3, Informative)

          by bsdaemonaut (1482047)

          In an incandescent light bulb the filament inside is approximately that hot. If you don't want to take my word for it, from http://en.wikipedia.org/wiki/Color_temperature [wikipedia.org], "An incandescent lamp's light is thermal radiation and the bulb approximates an ideal black body radiator, so its color temperature is essentially the temperature of the filament."

        • by cdrudge (68377)

          Did you REALLY think the filament of an ordinary incandescent tungsten bulb operates at 4940.33 degrees Fahrenheit (2727 degrees C)? Seriously?

          Um, yeah [hypertextbook.com], I do. Or at least I imagine that it's definitely within the realm of possibility for some light bulbs.

        • Re:800C? (Score:5, Informative)

          by Muad'Dave (255648) on Monday December 03, 2012 @10:36AM (#42168467) Homepage

          Did you REALLY think the filament of an ordinary incandescent tungsten bulb operates at 4940.33 degrees Fahrenheit (2727 degrees C)? Seriously?

          Yes, I do. [wikipedia.org] Absent phosphors, the only way for a filament to have a color temperature of 3000K is to be at 3000K. From the article:

          "An electric current heats the filament to typically 2,000 to 3,300 K (3,140 to 5,480 F)), well below tungsten's melting point of 3,695 K (6,191 F)."

          and

          "Tungsten is the metal with the highest melting point, 3,695 K (6,191 F). A 50-hour-life projection bulb, for instance, is designed to operate only 50 C (122 F) below that melting point."

    • Re:800C? (Score:5, Insightful)

      by hamjudo (64140) on Sunday December 02, 2012 @07:27PM (#42164095) Homepage Journal
      The very, very small area is probably a few orders of magnitude smaller than your concept of very very small. The ieee article says it will take months to test 1 billion cycles. There are on the order of 10 million seconds in 4 months, which means the researcher thinks he can test at the rate of 100 cycles per second. In other words, the regions are so small, it takes on the order of 10ms to cool enough for the next test cycle.
    • Re:800C? (Score:5, Informative)

      by timeOday (582209) on Sunday December 02, 2012 @07:35PM (#42164135)
      To prevent uncontrolled energy dissipation you can use a fuse.

      Fun fact: the spark plug in your car [wikipedia.org] creates a temperature of 60,000 K (a little over 107,000 F). A cheap 4" (100 mm) magnifying glass can generate a temperature of over 600C [blogspot.com]. So, like you said, it's all about duration and area.

      • by mysidia (191772)

        To prevent uncontrolled energy dissipation you can use a fuse.

        You can also use a resistor. Any battery will have an internal resistance, and most Lithium polymer and Lithium ion batteries will already have a safety circuit, to prevent an excessive rate of discharge.

        Also, the small wires from the battery act as a resistor -- they cannot deliver unlimited watts of power or amps of current.

        • by drinkypoo (153816)

          Also, the small wires from the battery act as a resistor -- they cannot deliver unlimited watts of power or amps of current.

          No, but if you have 00 wires to your batteries like I do, they can probably deliver anything the internals of the batteries can provide, assuming you can get the power from the terminal into the cable without having a corrosion problem or similar. When I got the truck I had bad battery cables everywhere, though, it seems to be a typical problem for the diesel f-series.

          Now, it's time for an automotive analogy! Well, maybe not an analogy, but the point is, my diesel has glow plugs and the glow plugs have a po

      • So, like you said, it's all about duration and area.

        And surrounding environment.

        Trigger that spark plug in normal air and not much will happen.
        Trigger it in an engine cylinder and the fuel-air mixture will ignite pushing the piston down with the cylinder wall containing the blast.
        Trigger it in an room filled with the correct fuel-air mixture and boom

    • What are the odds they'll let something that can heat up that much on an airplane, once they read this article? :\ More seriously, I assume this is over a very, very small area, and the chip dissipates that heat within a few minutes, and that it would only be warm to the touch for a few moments... but I still gotta ask: Is there the possibility of catastrophic failure? Like if the chip was maliciously reprogrammed to trigger all the heating elements simultaniously?

      The actual danger as a burn hazard/ignition source is still limited by the total battery capacity of the device(even assuming that the manufacturer entirely cheaped out on fuses or other protection). A hypothetical attacker could do as much damage, probably more, just by shorting the battery with a length of wire or a paper clip or something...

      • by icebike (68054)

        The actual danger as a burn hazard/ignition source is still limited by the total battery capacity of the device(even assuming that the manufacturer entirely cheaped out on fuses or other protection). A hypothetical attacker could do as much damage, probably more, just by shorting the battery with a length of wire or a paper clip or something...

        Good point. The fact that they let li-poly batteries on the plane is amazing enough. Something powered by said batteries would be far less risky.

        • There are, or were, some restrictions on air-freight quantities of the things; because they were suspected in a couple of cargo plane crashes(potentially hundreds-thousands of cells on a pallet, all it takes is one to be defective and you get a cascading failure-into-zesty-metal fire...), but I assume that they realized that grabbing everybody's cellphone, mp3 player, laptop, and everything else just wasn't going to fly.

          Having observed a few laptop battery packs decide to go out with a bang, I certainly wo

    • by mysidia (191772)

      What are the odds they'll let something that can heat up that much on an airplane

      Very high. The surface volume that can be heated to that temperature is microscopic.

      There would not be sufficient power available to heat anything non-microscopic to that temperature.

      The small amount of heat would be quickly dissipated over a massive surface area upon contact with anything else, so the 800 degree temperature of the cell is in no way shape or form, a danger.

    • If that was the case then what about the incandescent bulbs still found in some old flashlights or even in the "overhead lighting" above your seat?

      Do you know how hot that tungsten filament gets when energized?

      The total amount of *heat* being used for refreshing your memory chip will be infinitesimal by comparison to the average bulb filament. Remember -- temperature without heat is pretty harmless.

    • by kimvette (919543)

      The incandescent lamp still used as the backlight for many digital watches is allowed on aircraft, and it gets much hotter than that.

    • by dargaud (518470)
      Easy: put them on top of an AMD processor !
  • cant wait (Score:3, Funny)

    by Anonymous Coward on Sunday December 02, 2012 @07:27PM (#42164101)

    I cant wait for the first YouTube guide telling they should put flash memory in the oven to fix it. That will translate into baking cellphones ... and you know someone will try it.

    • A temperature like that is more like crematory than an oven. Does even a blow torch get 1400 F?

      • Re: (Score:2, Interesting)

        by Anonymous Coward

        What most people would call a blow torch is a common plumbing torch burning propane or propane/butane mix in air. It gets about 3600 F flames max. Burning with propane with pure oxygen gets about 5100 F max. The gent who talked about cutting steel was likely using an oxy-acetylene torch which gets a bit hotter at 6300 F max. Bit of trivia for this cutting method is that the heat is only needed to get the steel hot enough (kindling temperature) that the steel burns in the pure oxygen stream versus meltin

    • by jaxxa (1580613)
      My friend did that with his Galaxy S2 and it fixed the issue he was having. I dont know if it was the Flash memory as this article is talking about, but it worked.
      • He was probably reflowing the solder. Crappy solder / soldering jobs (such as those in the Xbox 360) are often fixed by heating up the solder to the reflow temperature. This liquifies the solder allowing it flow back into its proper place.
  • Interesting (Score:5, Interesting)

    by certsoft (442059) on Sunday December 02, 2012 @07:31PM (#42164121) Homepage
    Back around 1976 I was working in a group that used Intel 4004 processors and 1702A EPROM. They found they could get more program/erase cycles out of a 1702A if they periodically baked them in an oven.
    • Fun fact: baking in an oven is also the primary method to restore old analog recording tape that has stuck together during storage. http://en.wikipedia.org/wiki/Tape_baking [wikipedia.org]
  • The article hints that this tech is published but not patented. Way to go!

    If true we can expect many implementations in record time, lots of manufacturers trying out variations and producing affordable products.

    On the other hand, if they set huge license fees on the patent it is highly likely that the only licensees will fail to produce a successfull product, and at best it becomes a niche feature for systems where it has exceptional value. For spacecraft that cannot be repaired the value is huge, for yo

  • by Microlith (54737) on Sunday December 02, 2012 @07:59PM (#42164305)

    To reiterate my comment posted on Ars [arstechnica.com] two days ago when this popped:

    So it's sort of a mix between traditional flash technology and the mechanism by which PCM works.

    PCM does short pulses of between 400C and 700C to change the resistivity of the chalcogenide material, so generating these temperatures on microcircuitry like this isn't new.

    *PCM = Phase Change Memory;

    I suspect that 800C isn't out of reach, and the elements can be much coarser given you don't need them to alter a bit.

    • The older programmable logic chips of the seventies and eighties, such as bipolar PROMs and PALs, had a metal fuse for every programmed bit. Those fuses would be melted to program the chip. However, those days featured external programmers to do the melting.
  • by Yarhj (1305397) on Sunday December 02, 2012 @08:07PM (#42164361)
    This story has popped up a few places already, and 90% of the comments are always "800C! But what if it catches fire?"

    Yes, the floating gate is heated to 800C, but the volume of the heated area is on the order of a few hundred cubic nanometers. The energy involved in heating a volume that small is, well, incredibly small, and dissipates rapidly into rest of the chip. Your flash memory will not burst into flame. It will not require significantly more energy from your battery, and it will not require special clearance from the TSA to bring it on a plane.

    The real challenge here is not coping with high temperatures, but rather balancing the increase in cell lifetime with the increase in die size. If the 100 million cycles number is completely accurate, then there's not much question that this technology will make its way into a lot of flash, but if that upside is only for a few (or even most) of the bits on a die, then things get more complicated

    For more info run through the comments from the Ars Technica writeup of the same story: http://arstechnica.com/science/2012/11/nand-flash-gets-baked-lives-longer/ [arstechnica.com]
    • by KIFulgore (972701) on Sunday December 02, 2012 @11:12PM (#42165325)
      That's a good point... I've read a lot of comments from people freaking out about being able to bring these on a plane.

      I was once boarding a plane and accidentally scuffed my feet across the carpet. I brushed my hand by someone else and triggered a static arc that must have been close to 50,000 degrees. The plane was still able to take off. True story.
    • by jamesh (87723)

      Your flash memory will not burst into flame

      Challenge. Accepted.

  • by Miamicanes (730264) on Sunday December 02, 2012 @09:43PM (#42164951)

    Before everyone gets worked into frothy concern about flash write cycles, keep in mind that the #1 cause of failure & data loss on Sandforce-based controllers is a toxic mess of piss-poor proprietary firmware that's brittle, bitchy, and will brick the drive in self-defense if it corrupts its internal database, then decides you're trying too hard to salvage your data by trying to use something like dd_rescue on it. Oh, and their decision to save a buck by omitting the supercapacitor that's supposed to guarantee that it always has enough power to finish its current write.

    Read the Agility/Vertex 2 & 3 forums at ocz if you think I'm making this up. Basically, Sandforce drives have mandatory encryption that can't be disabled to maximize your odds of successful data recovery, but they also employ active countermeasures to detect "hacking attempts" that usually result in the drive ending up in "panic mode".

    I wouldn't touch a Sandforce-tainted SSD with a dirty, tetanus-infected pole. They deserve to be sued into oblivion by class-action lawsuits. At the VERY least, they should give us the option of setting our own encryption key (to a value WE know), and a way to rip the bits from a borked drive for offline recovery. The most infuriating thing about data death by Sandforce is the knowledge that 99.99% of your data is *there*, but you aren't allowed to recover it due to their fucked up business policy.

    • Back up your data and don't rely on a technology that degrades every time you write to it.
      • The problem with relying on backups is the fact that Sandforce SSDs fail so often, and fail in ways that traditional strategies (like RAID and SMART) simply can't deal with. We're talking about drives that would basically commit suicide if your UPS sneezed at the wrong moment, or for other reasons having nothing to do with power loss. Worse, we're talking about drives that can commit "synchronized suicide" and kill themselves in unison if you tried to depend upon RAID 5 or RAID 1 as a strategy for realtime

    • by g00ey (1494205)
      So even an Intel SSD drive with the SandForce controller shoud be avoided?

      Lately, the Samsung drives have become very popular but there is one caveat to them as well; they don't have a unique WWN like normal hard drives have. This drawback leads to problems using several SSDs on the same controller; the system cannot tell them apart. It's like a router or a switch cannot tell two computers apart because their NICs use the same MACs. Unlike NICs you cannot change the WWN of a Samsung drive.
  • I seriously doubt there will any detectable increase in the surface temp of the chip when this heating occurs, so that part of the story is a non-issue to me. What is much more important to me is extending the life span of the NAND flash, meaning SSD's and other devices using it will no longer have such a short useful life. I have not even considered buying an SSD so far precisely because of that. This technology, if it works as promised, will make me take the plunge! .
  • Not one of you seems to have caught the "baking for several hours at 250C has the same effect" part, so big question: could I bake my SSD at 250C (482F for us Americaners, and easily attainable in any kitchen oven) to restore it once I exceed the flash's write limit? Or will the caps pop, die packages (or even the PCB and its traces!) de-laminate, etc?

    Thanksgiving (and now Christmas) turkey fresh from the oven along with a freshened SSD sounds especially delicious!

    • The solder will melt. Reflow usually peaks at 260C. I think the problem is you need to heat die of the chip. Packages are only designed to take 260C for 10 seconds during the soldering process. You'd need to keep the heat on until the die gets up to 250.
    • by Osgeld (1900440)

      no everything around the die of the IC will start to burn well before it gets to temperature in an oven, electric ovens especially, are binary devices, your coil is not at 482 degrees, its full on hot as it can get, and basicly PWMed at a snails pace.

      if you ramped it up slow, and had a more controlled heat source yea maybe

    • by Mal-2 (675116)

      It would seem to me you'd be much better off with a soldering station (digital if you prefer) where you can aim all (carefully controlled) heat directly at the chip in question. It's not like they're stupidly expensive either, and they're enormously useful for all your standard soldering needs.

  • by Anonymous Coward

    Just place the flash on the board near my Pentium 4. I'm pretty sure it runs at 800C.

  • by metaforest (685350) on Monday December 03, 2012 @09:51PM (#42175287)

    ... is a really, really bad idea.

    The plastics used in IC packages tend to absorb moisture from the air. Over time this moisture gets trapped in the package. If you heat a plastic IC package that has been in service to 250C there is a pretty good chance it will 'popcorn' thus destroying the chip, and often visibly rupturing the package. It can be prevented by baking the board at 50 - 80C for 12 - 20 hours, but that is going to cause other problems. No one is going to be using reflow ovens to "reset" FLASH cells.

    As others have pointed out spot-heating a FLASH block to 800C would take an almost trivial amount of energy, and would only need to be done when a block fails an erase-write cycle, or as an idle task performed on blocks that have been reassigned from the 'in-use' pool to the 'dirty' pool, but have not yet been erased and assigned to the 'free' pool.

    The hardware required to implement this on an existing flash design would be almost trivial.

Please go away.

Working...