Slashdot Mirror


Phase Change Memory Points To Future of Storage

An anonymous reader writes "A UC San Diego team is about to demonstrate a solid state storage device that it says provides performance thousands of times faster than a conventional hard drive and up to seven times faster than current state-of-the-art solid-state drives. The drive uses first-of-its-kind phase-change memory, which stores data in the crystal structure of a metal alloy called a chalcogenide. To store data, the PCM chips switch the alloy between a crystalline and amorphous state based on the application of heat through an electrical current. To read the data, the chips use a smaller current to determine which state the chalcogenide is in."

70 comments

  1. *cough* Not the first of its kind. by Anonymous Coward · · Score: 0

    I suppose this will allow Micron to announce that skunkworks project that's been floating around since 2009 or so...

    1. Re:*cough* Not the first of its kind. by flatulus · · Score: 1

      Hardly skunkworks. PCM chips are in Micron's (Numonyx) catalog. I considered using one in a design last year, but they were too expensive, mainly because I only needed a wee bit of non-volatile storage and these chips only come in 128 Mbit density.

      You can buy them from Digikey at $4.57 each. But you have to buy them a tray at a time (576 parts per tray).

    2. Re:*cough* Not the first of its kind. by Anonymous Coward · · Score: 0

      Not the raw memory. The device that is the subject of the article is not the first of its kind.

  2. Similair to HP Memeristors by Anonymous Coward · · Score: 0

    I read something similar about HP memristors

    1. Re:Similair to HP Memeristors by X0563511 · · Score: 1

      Why thank you for this incredibly useful comment!

      --
      For large sets, this will be our guide even unto death, for the LORD will work for each type of data it is applied to...
  3. Shades of the Foundation! by hedronist · · Score: 1

    My very first reaction was to think of Asimov's Foundation trilogy and the fact the the Galactic Library was stored as nicked quanta in a paperweight on the Librarian's desk. The Barbarians allowed him to take his personal belongings with him before they destroyed the Library Planet.

    1. Re:Shades of the Foundation! by DanTheStone · · Score: 1

      Asimov's Foundation trilogy? Is that like "The fifth book in the increasingly inaccurately named Hitchhiker's Trilogy"?

    2. Re:Shades of the Foundation! by elfprince13 · · Score: 1

      My first reaction, whenever I read about crystalline storage, is "oh boy, Stargate IRL"

    3. Re:Shades of the Foundation! by irreverentdiscourse · · Score: 1

      Superman would like to have a word with you...

  4. Great for Self-Destruct Drives by DontLickJesus · · Score: 1

    No longer will I need a huge magnet, now I just need a hair dryer!

    But Seriously, wouldn't external heat sources pose a problem for such a technology? I don't want my drive erased next time my electricity goes out during the summer.

    --
    Where genius and insanity become confused true wisdom is found
    1. Re:Great for Self-Destruct Drives by bmo · · Score: 1

      >just need a hair dryer!

      Honey?
        yeah?
      Can I borrow your EZ Bake Oven?
        But daddy, the police took it last time...

      --
      BMO

    2. Re:Great for Self-Destruct Drives by 0100010001010011 · · Score: 1

      If you have issues with your house going 600C without AC you may have other issues. Not to mention high heats have just as detrimental effects on magnets.

  5. Uh-Oh by Anonymous Coward · · Score: 0

    Okay... atomic bombs are one thing, but now the aliens are really going to take notice. We're starting to use the same technology as them.

  6. Application of heat doesn't sound too hot... by blankinthefill · · Score: 2

    To store data, the PCM chips switch the alloy between a crystalline and amorphous state based on the application of heat through an electrical current.

    That seems like probably not a very good idea, and I'm sure it will end up being one of the major hurdles to this technology really getting off the ground. What happens when the memory is heavily used (leading to buildups of heat in the memory that could cause unintentional bit changes)? Obviously the heat used to flip the bits must be dissipated very, very quickly, and that's a pretty challenging problem in its own right. Also, what happens to system temps when you use this memory? Many systems are already difficult to keep cooled, and adding another source of heat could be a particularly bad idea. Heck, what if the increase in system temps leads to memory faults? After looking over the Wiki, the last question seems unlikely to be a problem, but heating something to >600C seems like it could make it very hard to use this tech in heavy use situations.

    1. Re:Application of heat doesn't sound too hot... by TheCouchPotatoFamine · · Score: 2

      It sounds a lot like magneto optical drives, like MiniDisc. It probably takes very high heat (good for room temp stability, i doubt your hairdryer would do it) in a *very* small place for a *very* short time. Probably, the stability is very good or they uh, wouldn't be excited about it. I don't think the dynamics of the room would be affected any more (probably less) then a typical HD. Check out: http://en.wikipedia.org/wiki/Magneto-optical_drive it's fascinating

      --
      CS majors know the time/space tradeoff, but they never get taught the 3rd, crucial, tradeoff of the set: comprehension!
    2. Re:Application of heat doesn't sound too hot... by elsurexiste · · Score: 1

      I saw this same principle being used on CDs: in the crystalline state, it reflects much more light than in the amorphous. IIRC, to change into crystalline, it required more than 130 C, but take it with a grain of salt. What I'm sure is that it was a lot hotter than 50 C, otherwise I would've thought the same as you.

      --
      I rarely respond to comments. Also, don't ask for clarifications: a brain and Google are faster, believe me!
    3. Re:Application of heat doesn't sound too hot... by Dragoon235 · · Score: 1

      As someone who has done research in memory wear leveling, I can assure you that these technologies have a place. There are significant design trade-offs that must be considered for any application. Power, area, speed/latency, and maximum amount of write-erase cycles all come into play. One of the head researchers in emerging memory technologies at Penn State has an interesting presentation here on the roles of these memory technologies (yes, I realized it is hosted at Oregon State, and he is from PSU, oh well...): http://web.engr.oregonstate.edu/~sllu/xie.pdf

    4. Re:Application of heat doesn't sound too hot... by Anonymous Coward · · Score: 0

      That seems like probably not a very good idea, and I'm sure it will end up being one of the major hurdles to this technology really getting off the ground.

      Good point. I'm sure the developers didn't think of that. You'd better warn them, quick - before they waste a bunch of R&D funds on this technology.

    5. Re:Application of heat doesn't sound too hot... by jbengt · · Score: 1

      Obviously the heat used to flip the bits must be dissipated very, very quickly, and that's a pretty challenging problem in its own right

      Fortunately, the smaller the memory element, the less heat it takes to raise its' temperature. And fortunately, or unfortunately, depending on your point of view, the smaller the memory element, the faster and easier heat dissipates from it. I'm sure that one of their criteria is to select materials that do not spontaneously switch states at the temperatures typically found in electronics. And another criteria would be to select materials that do not require an inordinate amount of power to effect the switch.

    6. Re:Application of heat doesn't sound too hot... by sjames · · Score: 1

      It's not as much heat as you might think it is, it's just very concentrated. Same reason you can use a laser to heat something hotter than the surface of the sun without even warming the room noticeably.

  7. 1.1 gigabytes per second - Fast ? by Anonymous Coward · · Score: 0

    Make that 8.8 gigabits per second compared to 6Gb/s hard drive. Doesn't sound revolutionary. There must be something in the other details that make this exciting.

    1. Re:1.1 gigabytes per second - Fast ? by NoSig · · Score: 1

      Make that 8.8 gigabits per second compared to 6Gb/s hard drive. Doesn't sound revolutionary. There must be something in the other details that make this exciting.

      The only way for the speed comparison to make sense so that we get a 1000x improvement on conventional harddisks and only a 7x improvement on flash is if speed is referring to latency instead of bandwidth, which is correct even if counter to normal marketing material. If the stated bandwidth is for a small element then you can add X of those elements to your drive to multiply the bandwidth by X, so possibly the bandwidth could be pretty good too.

  8. similar issues to flash by rubycodez · · Score: 1

    skimmed some papers on PCM on the web, looks like their goals are to get the memory to 100 million writes and 10 years retention of data; very similar issues to flash, it seems

    1. Re:similar issues to flash by TheRaven64 · · Score: 2
      Looks like you did just skim. PCRAM has two fundamental differences from flash:

      It's bit-erasable. You can write a single word to PCRAM, without having to do the read-erase-rewrite cycle that Flash requires over a large cell. This means that you can just map a PCRAM device straight into RAM and use it as (slowish) memory. This is great for things like applications - the entire binary can be run from the mass storage device, it doesn't need copying into memory (execute in place). For a mobile device, you could conceivably have PCRAM as your main memory and 256MB or so of DDR as level-4 cache. When you're in standby mode, power down the DDR entirely, and your power usage drops to zero. Unlike suspending to disk or flash, you can resume instantly.

      It's fast. Response times for PCRAM are somewhere around the 70ns mark, while flash is measured in ms. 70ns is about the speed of main memory a decade ago. This means that you can have non-volatile storage that's not much slower than RAM.

      --
      I am TheRaven on Soylent News
    2. Re:similar issues to flash by Anonymous Coward · · Score: 0

      This means that you can have non-volatile storage that's not much slower than RAM a decade ago.

      There, FTFY.

    3. Re:similar issues to flash by sjames · · Score: 1

      It would also get rid of much of the weirdness of SSDs. Most of that is because of the largish erase regions compared to block size for a filesystem and the time it takes to erase a sector.

  9. Moneta by roman_mir · · Score: 2

    So, what's up with the name of the system, "moneta", is it what I think it is (a Russian word for 'coin'), or is there something else at play here? I am a bit confused, because in the article, (which I am sorry to admit I read), it mentioned a bunch of names, but none that were Russian sounding.

    1. Re:Moneta by Anonymous Coward · · Score: 0

      Moneta is Italian, not Russian. Similar to Spanish "moneda".

    2. Re:Moneta by Anonymous Coward · · Score: 0

      Moneta was the Roman goddess of memory.

    3. Re:Moneta by roman_mir · · Score: 1

      It's also Russian, though it easily might have come into the language from other language, that's certainly a possibility, OK, but why call this tech a 'coin'?

    4. Re:Moneta by roman_mir · · Score: 1

      OK, that makes more sense than this Coin

    5. Re:Moneta by chebucto · · Score: 1

      Moneta was the Roman goddess of memory.

      It was also the name I gave to an set of in-house backup scripts I wrote a few years ago. If only I'd trademarked it!

      --
      The English word fart is one of the oldest words in the English vocabulary.
    6. Re:Moneta by TheRaven64 · · Score: 1

      Am I the only one who finds it amusing that someone called Roman didn't know that?

      --
      I am TheRaven on Soylent News
    7. Re:Moneta by Cyberax · · Score: 1

      Well, 'Roman' (with the stress on the second syllable) is a common first name in Russian as well :)

    8. Re:Moneta by roman_mir · · Score: 1

      Why is that a surprise, my first language is Russian, not Italian.

    9. Re:Moneta by Anonymous Coward · · Score: 1

      Check this out on Wikipedia:
      http://en.wikipedia.org/wiki/Moneta

      Goddess of memory...

    10. Re:Moneta by Sardaukar86 · · Score: 1

      Financial Crisis of 2008 explained in 2006 in detail in a video. [tinyurl.com]

      Offtopic: Thanks Roman_Mir, that was an excellent vid. Very interesting especially from a foreigner's point of view (kiwi)

      I encourage others to view at least the first five mins. I started out with this in mind and was hooked, ending up watching the entire hour-long clip.

      --
      ..Mullah or Pope, Preacher or Poet, who was it wrote: "Give any one species too much rope and they'll fuck it up"?
    11. Re:Moneta by roman_mir · · Score: 1

      Sure, he has a radio station and a bunch of businesses around the world doing investments and now even banking it seems, so if you liked what he had to say in that vid, you should research some more.

    12. Re:Moneta by Sardaukar86 · · Score: 1

      ...so if you liked what he had to say in that vid, you should research some more.

      That seems wise. What I've learned today is clearly the tip of the iceberg and some further investigation on my part is in order.

      Collectively we younger Western nations seem to fit the 'short-term thinking' mould pretty well; meanwhile those nations that take the long view are just starting to reap their rewards. Those rewards are going to come thick and fast, aren't about to slow down anytime soon and will not include the West.

      --
      ..Mullah or Pope, Preacher or Poet, who was it wrote: "Give any one species too much rope and they'll fuck it up"?
    13. Re:Moneta by roman_mir · · Score: 1

      Possibly an interesting compilation I put together. Just fun to look at.

  10. Density? by bryan1945 · · Score: 1

    I actually skimmed the article and I didn't see any mention of data density. Anyone know how it compares?

    --
    Vote monkeys into Congress. They are cheaper and more trustworthy.
    1. Re:Density? by Anonymous Coward · · Score: 0

      You can download the datasheets for the micron pcm modules they use at http://www.micron.com/products/pcm/

    2. Re:Density? by bryan1945 · · Score: 1

      Thank you, Mr. AC!

      --
      Vote monkeys into Congress. They are cheaper and more trustworthy.
  11. Heat from RAM is different. by Anonymous Coward · · Score: 0

    RAM is hot because the entire DIMM has to switch transistors to maintain the current state of memory. The heat in this instance would be involved in reading and writing only the portion in use at that moment. The circuits that handle the memory bus communication would be continuously active, so that might be a local problem area for the device. Does NVRAM get hot like RAM does? I don't have numbers but my understanding of the technologies suggest not.

    1. Re:Heat from RAM is different. by GameboyRMH · · Score: 1

      I had a PDA with NVRAM and I never noticed it getting more than slightly warm - and if the memory did get significantly hot, it would have drained the battery very fast.

      --
      "When information is power, privacy is freedom" - Jah-Wren Ryel
  12. we want the power by Anonymous Coward · · Score: 0

    what about power consumption? that's the real showstopper nowadays

  13. Interesting but... by hahn · · Score: 1

    Phase change memory tech is not new as most readers here will know. Nearly all the major semiconductor companies have worked on prototype versions of this tech. If companies like Samsung and Intel haven't succeeded in mass producing it yet, as a consumer I'd be more interested in knowing what sets this particular device apart from all the others that will make it more likely to reach the market for the masses. Cheaper to produce? Scales more easily? More energy efficient? More stable?

    --
    "The only normal people are the ones you don't know very well."
    1. Re:Interesting but... by networkBoy · · Score: 1

      Intel did succeed, but sold the assets to Numonyx.

      --
      whois gawk date unzip strip find touch finger mount join nice man top fsck grep eject more yes exit umount sleep dump
  14. Aside from heat issues and built up by h2okies · · Score: 1

    Is what is the number of cycles before a given bit can no longer be changed. Will this outlast the current SSD write cycle limitations that are getting smaller not longer with the ever shrinking die size thus resulting in having to have 2x or 4x the actual advertised RAM installed to meet ever increasing MTBF rates..

    --
    Beware the Lollipop of Mediocrity, Lick it once and you suck forever.
  15. Sounds like it works fine until you lose power.... by Fallen+Kell · · Score: 1

    If it works as described with the PCB generating heat to change the substance from a crystal to a liquid, once that heat is removed via loss of power, all would change back to a crystal, and you would lose all your data. This may be fine for RAM, but not for storage.

    --
    We were all warned a long time ago that MS products sucked, remember the Magic 8 Ball said, "Outlook not so good"
  16. Interesting comparisons by Captain+Spam · · Score: 1

    A UC San Diego team is about to demonstrate a solid state storage device that it says provides performance thousands of times faster than a conventional hard drive and up to seven times faster than current state-of-the-art solid-state drives.

    I don't know why, but the speed comparisons in the summary amuse me. "This is THOUSANDS of times faster than a conventional hard drive — absolutely phenomenal speed gains, faster than anything else ever seen in the conventional hard drive world , speeds which will blow your mind straight out of your skull with how much blindingly faster they are than conventional hard drives, literally THOUSANDS of times faster — and kinda sorta faster than solid-state drives."

    --
    Demanding constant attention will only lead to attention.
    1. Re:Interesting comparisons by dgatwood · · Score: 1

      It reminds me of this:

      Space is big. You just won't believe how vastly, hugely, mind-bogglingly big it is. I mean, you may think it's a long way down the road to the chemist's, but that's just peanuts to space.
      —Douglas Adams

      --

      Check out my sci-fi/humor trilogy at PatriotsBooks.

    2. Re:Interesting comparisons by robot256 · · Score: 1

      Yeah, you're right, that is kind of distracting. That it's sorta faster than solid state drives is nice, but what we really want to know is if it has better power, reliability, or density. Given the recent fuss about SSDs failing with no warning, it would also be relevant to compare the data retention reliability of PCM with magnetic hard drives, but certainly not the speed.

    3. Re:Interesting comparisons by michelcolman · · Score: 1

      Yes, I didn't know solid state drives were already hundreds of times faster than hard disks.

    4. Re:Interesting comparisons by ShakaUVM · · Score: 1

      >>Yes, I didn't know solid state drives were already hundreds of times faster than hard disks.

      Heh, you're right. Consumer grade SSDs aren't hundreds of times faster than a HDD. Maybe one order of magnitude faster at sustained combined read/write (my SSD benched in at only 3x faster than my new HDD), but the real gain is in latency. Maybe that's what they meant by "faster". =)

    5. Re:Interesting comparisons by bobbozzo · · Score: 1

      They are, if you measure in I/O operations per second (IOPS), which is how enterprise-grade storage is often measured.

      --
      Nothing to see here; Move along.
  17. Re:Sounds like it works fine until you lose power. by Tapewolf · · Score: 1

    If it works as described with the PCB generating heat to change the substance from a crystal to a liquid, once that heat is removed via loss of power, all would change back to a crystal, and you would lose all your data. This may be fine for RAM, but not for storage.

    Actually I think you'll find it's the same material and a similar principle to CD-RW disks. The difference is that in CD-RW they are heating it with a laser, and reading it back optically. In PC memory, they are probably heating it electrically, and they are using a change in resistance rather than a change in reflectivity to read it back.

  18. What exactly have they built? by Zouden · · Score: 1

    I'm struggling to understand what these researchers have made, exactly. They certainly didn't invent phase-change memory, and the article states that this "Moneta" uses memory modules from Micron Technology. The wikipedia article mentions Samsung started shipping modules last year, ready for use in mobile applications. So clearly PCM has been available for some time. So perhaps Moneta is an actual device available for end users? That would be exciting!

    Swanson hopes to build the second generation of the Moneta storage device in the next six to nine months and says the technology could be ready for market in just a few years as the underlying phase-change memory technology improves.

    So it's not ready then. I really cannot see what these guys have achieved.

    --
    "A week in the lab saves an hour in the library"
    1. Re:What exactly have they built? by daedae · · Score: 1
      You quoted one part of the article, but you missed the relevant bit.

      "We've found that you can build a much faster storage device, but in order to really make use of it, you have to change the software that manages it as well. Storage systems have evolved over the last 40 years to cater to disks, and disks are very, very slow," said Swanson. "Designing storage systems that can fully leverage technologies like PCM requires rethinking almost every aspect of how a computer system's software manages and accesses storage."

      So you're right, they didn't invent PCM, but they're coming at the problem with the assumption that PCM will become commonplace and then looking at the problems that come after that. All the speed and capacity in the world are only helpful up to a point if your software stack and memory bus are bottlenecks.

    2. Re:What exactly have they built? by daveman_1 · · Score: 1

      I've spent all of two days now reading about PCM, but here's an observation: The lessons learned in making NAND flash work as a high-speed storage medium are applicable here as well. Many of the problems are the same, with the need for wear-leveling and optimization of write performance. The solutions appear to be somewhat different though. Their wear-leveling algorithm does not at all resemble the complexity of a typical FTL and I think that's the point.

      Dealing with the problems of getting this technology to scale are simpler and cheaper to address than those presented by NAND flash, if only because in-place writes are now back on the table, with no erase-before-write cycle. This technology looks like it needs to ramp up in density though before it's a viable alternative to current NAND flash. 40 chips for 10GB on a DIMM is not going to get much done inside a 2.5" SSD case.

      I also did not think their comparison to PCIe-based SSDs was fair. They called these 'state of the art', when the best SSDs are currently designed around use over a SATA3 bus and have performance figures much higher than those quoted.

      --
      Russian Russian Russian RussianDollSig DollSig DollSig DollSig
    3. Re:What exactly have they built? by daveman_1 · · Score: 1

      Actually, it's 40 chips for 640MB on a DIMM. The sample they demonstrated was 10GB in total.

      --
      Russian Russian Russian RussianDollSig DollSig DollSig DollSig
  19. Re:Sounds like it works fine until you lose power. by TheRaven64 · · Score: 1

    No. Power is needed for the phase change (flipping a bit). PCRAM is non-volatile - it does not require power to retain its state. That's the entire point...

    --
    I am TheRaven on Soylent News
  20. Interesting by SuperTechnoNerd · · Score: 1

    "switch the alloy between a crystalline and amorphous state"
    Interesting, this is similar how cd/dvd-rw works, where they use a laser to do the state change.

  21. Re:Sounds like it works fine until you lose power. by robot256 · · Score: 2

    It's not switching between solid and liquid. It's switching between crystaline and amorphous solid (stated in the first wikipedia intro, second link in the article). It takes a small amount of heat to make it switch between the two states, and they have different properties that can be measured, but both states are static in the absence of heat. What you described would make no sense at all, since if the PCB knows to provide heat to certain places then it already has external memory.

    Of more interest is the security of the data stored in PCM. Can you erase it by putting it in a microwave? Leaving it in a hot car? Will it be easy to make a microwave beam/laser to erase parts of the drive from outside? The answer is probably no, but it will be very interesting to see the temperature specs on the resulting consumer products.

  22. Not New But Apparently Improved by Anonymous Coward · · Score: 0

    The pioneer in the technology was Sanford R. Ovshinsky who called the technology Ovonics and whose company Energy Conversion Devices has been in business for a long time. What is perhaps different about the new devices is improved speed and increased storage size.

    I was interested in these materials in the 1970's as a substrate for a different kind of computer architecture. They were the starting point for my development of Brain Models that are not computers.

    Bob Kovsky
    www.quadnets.com/td/td.html
    www.quadnets.com/sitemap.html

  23. glory whoring 101 by Anonymous Coward · · Score: 0

    The drive uses first-of-its-kind phase-change memory,

    In the 1960s Stanford R. Ovshinsky of Energy Conversion Devices first explored the properties of chalcogenide glasses as a potential memory technology. In 1969, Charles Sie published a dissertation,[1][2] at Iowa State University that both described and demonstrated the feasibility of a phase change memory device by integrating chalcogenide film with a diode array.

    I understand everybody wants a crack at the recognition of being "the first", but c'mon, "first-of-its-kind"? Hardly.

    Even in that second quote from wikipedia, It almost looks like friends of Ovshisky slip his moniker in ahead of somebody (Sie) who actually appears to have done all the heavy lifting."60's" versus "1969" with no refereed publication to support claims .....hmmm.....can we be a little more vague here.

  24. Told oyu it was coming by Khyber · · Score: 1

    OUM/OVM memory for storage applications. The IOPS should be quite nice once done properly.

    --
    Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
  25. Metal alloy? by Anonymous Coward · · Score: 0

    Chalcogens (Oxygen, sulfur, selenium, etc.) are on the wrong end of the periodic table to be part of a metal alloy.
     
    Maybe they meant "ceramic" instead?

  26. still a lot slower than RAM by Anonymous Coward · · Score: 0

    idea, run everything in ram, archive image to even a slow hard drive .....

    or have RAM able to be backed up with lithion, type batteries, such that you can shut everything else down, cpu, hard drives,,,vid card ...fans...and keep the image in ram, i'm thinking about something like that with one of these server boards with lots of ram slots, asus makes on, 128gig/256gig

    even 8 gig RAM drive setup, even if i had to pull from a hd, and copy the 8gig back into memory every time, how long does that take?

    on that asus board does anyone even make 16gig sticks?

    1. Re:still a lot slower than RAM by Savantissimo · · Score: 1

      see: http://www.physorg.com/news/2011-05-samsung-mass-30nm-class-gigabyte-memory.html

      Samsung has had 32GB/40nm sticks out for over a year, 16GB out for 2 years, now they are about to ship the 30nm 16/32GB modules with lower power consumption. Price per GB is bad.
      Memory4less has:
      Samsung 16GB PC3-8500 DDR3-1066MHz ECC Registered CL7 240-Pin DIMM
      ~$950, other speeds for more $
      32GB sticks run ~$2,150 and up
      = about 6 to 7 times the cost/GB of vanilla 4GB sticks on newegg, or about 3 to 4 times the cost/GB of 8GB ECC sticks.

      --
      "Is life so dear, or peace so sweet, as to be purchased at the price of chains and slavery?" - Patrick Henry