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

 


Forgot your password?
Close
typodupeerror
×
Intel Hardware

Intel Set To Demo PRAM 83

Posted by kdawson from the flashier dept.
xavatarx writes "Intel's chief technology officer Justin Rattner is set to give the first public demonstration of the company's PRAM (phase-change RAM) technology at this week's Intel Developer Forum conference. 'Intel and other companies are counting on PRAM to replace both NOR and NAND flash memory to generate the demand required to produce the new memory chips in volume, and drive down costs,' the article says."
This discussion has been archived. No new comments can be posted.

Intel Set To Demo PRAM More

Intel Set To Demo PRAM

Comments Filter:

  • Quite the demo (Score:5, Funny)

    by stratjakt ( 596332 ) on Tuesday April 17, 2007 @05:30AM (#18764855) Journal
    The guy is going to look like a real froot-loop. [babycentre.co.uk]

  • AMD set to reply (Score:3, Funny)

    by bad_fx ( 493443 ) on Tuesday April 17, 2007 @05:32AM (#18764867) Journal
    AMD have announced they will shortly demo "BABYCARRIAGE" in response.

  • PRAM is new? (Score:5, Funny)

    by Xenex ( 97062 ) * <xenex@noSPaM.opinionstick.com> on Tuesday April 17, 2007 @05:33AM (#18764869) Journal
    Apple have been putting it in Macs for years! [apple.com]

    • Re:PRAM is new? (Score:5, Informative)

      by holle2 ( 85109 ) on Tuesday April 17, 2007 @05:38AM (#18764903)
      Well:

      Apple PRAM == Parameter RAM
      Intel PRAM == Phase-change RAM

      While:
      Parameter RAM == Any kind of conventional (probably non volatile) RAM
      Phase-change RAM == New kind of non volatile RAM using a new phase change technology

      Thus:
      Apple PRAM != Phase-change RAM

      QUED.

      • Question on how PRAM works and is manufactured (Score:5, Interesting)

        by asliarun ( 636603 ) on Tuesday April 17, 2007 @06:01AM (#18765001)
        A lay question, and I had asked this question in the previous /. thread about PRAM, but did not get an answer..

        How are Intel and others managing this chalcogenide glass manufacturing in their usual silicon DRAM process? Is this glass fused/bonded to silicon or something? Or is it an alloy.. and if so, is it a non-silicon alloy (silicon is a non-metal)?

        I tried the wikipedia entry on this subject (http://en.wikipedia.org/wiki/Phase-change_memory) , but couldn't completely understand:-
        a. How it really works in an electronic circuit and in a microprocessor (how do you control the heating/cooling at the chip level so that phase change occurs)?
        b. How it is supposed to be volume manufactured? Would they require a new fab entirely to manufacture PRAM (if they do decide to commercialize this technology), or can an existing fab be retro-fitted to support this manufacturing process?

        Appreciate any insights on this subject. At a high level, this does sound like a very exciting new technology.

        • Re:Question on how PRAM works and is manufactured (Score:5, Informative)

          by Hal_Porter ( 817932 ) on Tuesday April 17, 2007 @06:53AM (#18765211)
          I found this paper.

          http://www.ovonyx.com/tech_html.html [ovonyx.com]

          It sounds like the chalcogenide is deposited as a thin film. Mind you they talk about transistors, so it must be an extra processing stage on a normal chip.

          This seems to confirm it
          http://www.eetimes.com/in_focus/silicon_engineerin g/OEG20030919S0044 [eetimes.com]
          Chalcogenide RAM is nonvolatile, boasts access speed comparable to that of DRAM and possesses advantages in scalability, high sensing margin, low energy consumption and endurance to cycling. The structure and processing of chalcogenide memory are much simpler than in other next-generation memories such as MRAM and ferroelectric RAM. In a chalcogenide memory cell, the data is stored in a flat chalcogenide layer that can be deposited near the end of the CMOS interconnect process. Therefore, disturbance of the CMOS process is minimal, making it ideal for systems-on-chip.

          So I guess they add an extra step to the end of the process and deposit a layer of chalcogenide glass.

          These things sound really cool BTW, they're writable at a byte granularity in tens of nanoseconds just like a regular SDRAM, but they are non volatile. It looks like they can flip bits individually either way too.

          Whereas flash memory is much slower - tens of microseconds per byte, and you need to erase 16K-128Kbyte block at a time. And PRAM is supposed to be denser and allow unlimited erase cycles.

          Plus Intel is backing it so it's not like it will fail because the vendor can't afford to scale the production process to make chips with a high capacity.
          • It's not unlimited in writing. It's got an expected life of 10^8 writes/reads. I've been watching this for years, now, and I'm surprised nobody even bothered to check some of my previous posts that mentioned this technology beforehand. I'm already using an Ovonix-made test drive in this machine - Windows loads up within 4 seconds. On my 5400 RPM 80 gig HDD, it takes about 14 seconds. VAST improvement, and yet another breaking of the bottleneck in hard drives. I couldn't be happier.
            • It's not unlimited in writing. It's got an expected life of 10^8 writes/reads.

              It's still better than 10^5 writes for flash. And even that is more than enough if you wear level over a large array, as I pointed out here -

              http://slashdot.org/comments.pl?sid=183698&cid=151 80090 [slashdot.org]
              "If you could wear level over 32GB, it would be 744 years, assuming you write a 100K/sec sustained"

              I've been watching this for years, now, and I'm surprised nobody even bothered to check some of my previous posts that mentioned this

              • Re: (Score:2)

                by Surt ( 22457 )
                Unfortunately, the quote you made is quite right, except that you want to write at a rate 10k greater in order to beat out hard disks, so that 0.744 years instead of 744, which doesn't look so hot (or 7 years if you're willing to accept a drive that is almost as fast as a conventional drive, which is almost acceptable). You also assume that wear levelling means getting the statistical average number of writes out of every cell, which it doesn't. Realistically, that factor chops off roughly half of your wr
                • Unfortunately, the quote you made is quite right, except that you want to write at a rate 10k greater in order to beat out hard disks, so that 0.744 years instead of 744, which doesn't look so hot (or 7 years if you're willing to accept a drive that is almost as fast as a conventional drive, which is almost acceptable).

                  I measured the write rate on my desktop machine, which was building software at least half the time. It's the average write rate, not the peak one. Even though a modern hard disk can write a
                • "Unfortunately, the quote you made is quite right, except that you want to write at a rate 10k greater in order to beat out hard disks, so that 0.744 years instead of 744"

                  Eh? We just want to beat out hard disks because they are mechanical, slow spinning up, slow reading, slow seeking, noisy, energy hogging, big, untrustworthy SOB's. Most of us couldn't care less on the number of write cycles, as long as the filesystem and OS portions of it can be written over many times within the life time of the equipment

            • It's not unlimited in writing. It's got an expected life of 10^8 writes/reads.
              10^8 writes/reads?! Do _reads_ also count?!
          • chalcogenide

            chal-ko-gen'-ide ?
            chal-cog'-en-ide ?
            sh-alko'-gen-ide ?
            fawstuh-grhants-dhaling ?

        • Re:Question on how PRAM works and is manufactured (Score:5, Funny)

          by LaughingCoder ( 914424 ) on Tuesday April 17, 2007 @07:49AM (#18765441)

          How are Intel and others managing this chalcogenide glass manufacturing in their usual silicon DRAM process? Is this glass fused/bonded to silicon or something?
          If that is your idea of a lay question, I'd hate to be hit with one of your "expert" questions.

        • Re: (Score:2, Informative)

          by Mystic Pixel ( 911992 )
          The structure of the silicon wafer is, in certain respects, similar to glass. The main difference is that "glass" (in the everyday sense) is an amorphous solid -- the atoms are basically jumbled together -- whereas the atoms in wafer silicon form a regular crystal lattice. The upshot of this is that, with a little cleverness, it's easy to deposit a wide variety of different substances in a layer on top of an exposed wafer surface, and have them stick fairly well. And, depending on the characteristics of sa

      • Re:PRAM is new? (Score:4, Funny)

        by Hal_Porter ( 817932 ) on Tuesday April 17, 2007 @06:33AM (#18765121)
        I believe Xenex was pretending to confuse two acronyms for humourous effect.

        I suggest you add him to a list of humans that use humour, and ensure your emotion emulator is powered up before replying to posts by humans on that list in future. It is very important that the humans here do not realise that we are not like them.

        • Re: (Score:2)

          by tepples ( 727027 )

          I suggest you add him to a list of humans that use humour, and ensure your emotion emulator is powered up before replying to posts by humans on that list in future.
          Do you have any links to descriptions of the appropriate behavior of an emotion chip? Some of us with Asperger syndrome would benefit from learning about emotion engines other than the one in the PlayStation 2 console.
          • Humour can't be expressed as an algorithm. I have a wonderful proof of this, but this post is too small to contain it.

      • Re: (Score:3, Informative)

        by carpe_noctem ( 457178 )
        Not to nitpick your post, but I thought you'd like to know that it's QED, not QUED... it's short for "quod erat demonstrandum", from Latin. :)

      • Re:PRAM is new? (Score:5, Funny)

        by Ant P. ( 974313 ) on Tuesday April 17, 2007 @09:05AM (#18766033)
        Apple *does* have phase-changing RAM... it changes from solid to smoke, you'll only see it in certain laptops with sony batteries though
      • I bet parties are a blast when you're around!
      • QED = Quod erat demonstrandum.
        QUED = ?
      • You can't honestly have not heard air being displaced somewhere over your head during that post, could you?
      • You mean like Gundam Seed? It all changes colors and becomes invincible?

    • Re:PRAM is new? (Score:5, Funny)

      by jrumney ( 197329 ) on Tuesday April 17, 2007 @06:05AM (#18765017)
      PRAM is so last year. I'm into PUSHCHAIR already, and looking forward to move to TRICYCLE real soon now.

  • Obligatory Monty Python... (Score:1, Funny)

    by Anonymous Coward
    I have to push the pram-a-lot.

    On second thought, let's not go to Camelot. (It is a silly place.)

    • Re: (Score:1)

      by AP31R0N ( 723649 )
      When fark had this article yesterday the FIRST post was "I have to push the PRAM-a-lot. Why the buggery bullocks did it take so long on /.?

  • Again? (Score:5, Interesting)

    by maxwell demon ( 590494 ) on Tuesday April 17, 2007 @06:31AM (#18765117) Journal
    Well, we've already seen MRAM [wikipedia.org] and FeRAM [wikipedia.org], both already in production. None of them seem to have replaced Flash or even DRAM yet. So what is it about PRAM that one should expect it to be different?

    BTW, is there anywhere a concise table comparing the characteristics of different RAM technologies?

    • Re:Again? (Score:5, Informative)

      by SnowZero ( 92219 ) on Tuesday April 17, 2007 @08:08AM (#18765563)
      Well it looks like PRAM is already winning on the practicality front. Two companies have PRAM chips at 128Mb or larger, and claim good density numbers. MRAM has only reached ~16Mb last I knew (although smaller ones can be bought right now). FeRAM, at least from Wikipedia, seems to suffer from density problems, as it can only be built on 350nm generation fabs (i.e. very old).

      The only thing not mentioned is cost, but if it scales (Intel thinks it does), and the special glass just adds only one step to manufacturing (which the original developer claims), it doesn't look like there are too many roadblocks to success. Now, claiming it will replace DRAM may be a little premature, however there's a good hope they can replace flash at least.

      • Re:Again? (Score:4, Informative)

        by Khyber ( 864651 ) <techkitsune@gmail.com> on Tuesday April 17, 2007 @09:24AM (#18766201) Homepage Journal
        You're not replacing DRAM with this stuff. DRAM is meant for far more read/write cycles than what this can do. This is a replacement for storage, not random access memory, due to the limited 10^8 read-write cycles (which any idling computer would eat up just running processes within a few days, or could go thru just running one game given sufficient complexity) As an upside, I'm playing with a test drive made by Ovonyx right now - Things load so fast you'd think "When did Windows become so damned efficient and speedy?" Four second boot time? Oh hell yes!
      • > Two companies have PRAM chips at 128Mb
        Well, if they are competing against current NOR flash, then they have a bit to go. Currently NOR flash is available at 1GB.
        Another thing they don't mention is if it's available in low power (ie. 1.8V), that's important if they want to target the mobile phone market.
        It does have the avantage of being faster and more reliable.
        I presume it will remain a niche product for a number of years until they can scale it up.

    • How? Intel is a supermassive chip company w/FABS. (Score:5, Insightful)

      by burnttoy ( 754394 ) on Tuesday April 17, 2007 @08:31AM (#18765765) Homepage Journal
      Only real men have fabs yadda yadda and Intel probably reckon that for every x86 chip they sell they can sell a couple of gig (or more) of PRAM as well. Intel need stuff for their fabs to manufacture or they cost a lot of money.

      There are 2 ways they can win assuming they have the capacity for massive scale manufacturing, which they seem to.

      1 - They can undercut the cost of NOR/NAND chips in the market place.
      2 - they can sell at price parity with NOR/NAND but solve the serious technical problems with both designs. TBH neither is terribly nice to interface to and both are very slow compared to DRAM. Beating the technical problems are explained to PHB's as Instant Boot (suspend to RAM - except its PRAM, not battery backed DRAM). Quietness. The G shocks required to actually damage the stuff as compared to a spinning HD. etc etc...

      Actually there's a lot of reasons to go for it. Not least of all that HD sizes on consumer products (cheapo laptops etc) seem to be stuck at 80 gig. It's cheap and most (not all - I've a terabyte+ of storage and still run out) users will never fill it anyway. Instant boot is a real serious seller - 2 minutes of boot time feels a lot longer as you can't do anything for 2 minutes.

      But, personally, I think Intel's massive production capability and their endless search to find something to do with all those billions of transistors is where they'll "win".
      • Not to burst your bubble, but PRAM and processors are incompatible at a FAB level.
        AFAIK Intel has spun their flash FABs off under their memory devision, and only produce flash at these FABs, presumably they will do PRAM there as well.
        -nB
        • They don't have to be fab process compatible. If the customer wants a CPU and Intel says - "Hey! We've got cheap and lovely NVRAM! Wnat a bucket full?" then the customer will buy both products from the one shop.

          • Intel need stuff for their fabs to manufacture or they cost a lot of money.
            I was responding to that statement, thus that they are FAB incompatible is contradictory to your initial post, at least as far as using it as a FAB filler.
            -nB
  • Yeah, we already have a McLaren buggy (http://www.ciao.co.uk/McLaren_Techno_Buggy__52819 92 [ciao.co.uk]) amd a Porsche pushchair (http://shop3.porsche.com/international/kids/babyc arriage/wap04050016/ [porsche.com]), why not an Intel pram.

    Oh, wait...

    • Re: (Score:2)

      by SnowZero ( 92219 )
      Furthermore, will Intel make a "dual-core" model for those with twins?... or will they just make an "HT" model just 15% wider that they claim is for twins?

  • Clarification (Score:5, Informative)

    by Xiroth ( 917768 ) on Tuesday April 17, 2007 @06:56AM (#18765227)
    Just to clarify (I'm an insta-buff on the subject from the wikipedia article [wikipedia.org]), despite having RAM in its name this is more a storage solution than a memory solution.

    I'm generally more a software person than hardware, but there's a lot to be excited about with this. It's apparently got a r/w time only 2-3 times the time of DRAM, and holds a lot of potential for things like paging files and storing frequently used software since there doesn't seem to be a limitation on the number of writes that can be applied. Once things develop, the technology might even be a ludicrous-speed replacement for hard-drives, as the storage mechanism is quite stable (more so than flash). I can definitely see this taking off in the future, if it delivers what it promises (and nothing else supercedes it in the meantime).

    • Re: (Score:2)

      by Junta ( 36770 )

      Once things develop, the technology might even be a ludicrous-speed replacement for hard-drives
      Will it glow plaid?

    • Here's the issue (Score:5, Insightful)

      by Bozdune ( 68800 ) on Tuesday April 17, 2007 @08:27AM (#18765721)
      There have been lots of proposals to use "slow RAM" throughout the years, and there's even been real hardware that tried to take advantage of it in various ways.

      A interesting example is the IBM 2301 drum memory device. Originally used as main memory, 2301's were later converted to paging devices. They had great transfer rates, but they became obsolete as soon as RAM sizes increased enough to cache a reasonable number of pages.

      The reason is that even though "slow RAM" like drum memory seems intuitively useful as a "third stage" paging device, if you do the math versus the two-stage combination of very fast RAM and very much slower disk, you find that the RAM/disk combo performs almost as well. The conclusion therefore has been that it makes little sense to throw away your money on medium-speed RAM, because you'd have gotten more bang for the buck by spending it either on (a) more fast main memory, or (b) bigger/better disks.

      Finally, if you look at history, the rotating storage industry continues to confound all of these "fast RAM" technologies by increasing performance and dropping $/bit at an amazing rate. Nothing is more primitive, to my mind, than spinning a disk platter in 2007 -- but there's still nothing better, and the technology shows no sign of dying.

      • Re: (Score:3, Insightful)

        by hackstraw ( 262471 )
        Nothing is more primitive, to my mind, than spinning a disk platter in 2007 -- but there's still nothing better, and the technology shows no sign of dying.

        In working with large numbers of computers over the years, here are my informal statistics for failure. 1) hard drives 2) power supplies 3) other, almost at the noise level

        And look at what the industry adds redundancy for in computers. 1) hard drives and 2) power supplies.

        Sure, anyone that thinks about it will agree that spinning disk platters in 2007 i
        • While i generally agree with your post, you are REALLY wrong with your "50 years" estimation.

          Seriously.
          Maybe 20 years, but not much more.
          • While i generally agree with your post, you are REALLY wrong with your "50 years" estimation.

            Seriously.
            Maybe 20 years, but not much more.

            Sure, I could be wrong, but there is no technology beyond tapes/disks that can store massive amounts of data _without power_.

            Personal computers are now typically in the hundreds of gigabytes today. "Enterprise" computing is commonly in the terabyte range. Research/scientific computing is commonly in the petabyte and beyond.

            It was only recently that tapes and disks replac

      • Re: (Score:3, Interesting)

        by jhfry ( 829244 )
        I used to maintain an IBM Pi2 Mini Computer that had drum storage up until the late 90's. I really like the idea, a read/write head per track eliminated all seeking and made for very predictable response times for our real time processing requirements.
        I would love to see the hard drive industry start incorporating more read heads in to drives.

        Imagine a single drive with two armatures, servo's and read/write heads. You could effectively double the throughput, reduce seek times, and improve latency. It wou

        • Re: (Score:1)

          by Pikoro ( 844299 )
          The idea I had about 10 years ago was to keep the spinning platters, but have a single bar across the span of the platter. that bar would have pickups (heads) along the side facing the platter, hence, the only moving part would be the spinning platter itself.

          Basically, if you took a slice of the disc where the bar was, it would be similar to this (when looking from the top:

          (======o======)

          The bar would contain thousands of heads (1 per track) on each side of the hub. you could place these bars on the top an

          • Re: (Score:2)

            by jhfry ( 829244 )
            The problem with this is that the cost of the heads would probably be prohibitively expensive. You are talking about a shitload of heads to cover every track, on both sides of ever platter.

            This is essentially what a drum storage unit did... it had a cylinder that rotated very quickly it's outer surface was coated with magnetic material that was manipulated by a bar of read/write heads. The only reason these are not still in use today is that the number of tracks have become so high that a head/track is f

      • Re: (Score:2)

        by mandolin ( 7248 )
        Hmmm ... I think your argument ignores boot times. If all you have is volatile RAM and slow disk, your boot times go into the crapper. (This ignores the recently-announced flash-hybrid HDDs, but ummm isn't the flash part a "3rd-stage paging device"?)

        Besides the reliability improvement another poster mentioned, PRAM also should have lower power draw, and less heat, than an equivalent HDD or hybrid setup. Also, HDDs aren't ramping up their performance like they once were (but if PRAM gave them an incentiv

        • Re: (Score:2)

          by Bozdune ( 68800 )
          I'd argue that slow boot is a software problem, not a hardware problem. The transfer rates from hard drives are plenty fast enough to provide near-instant boot, if anyone cared enough to engineer it. Two things stand in the way: (1) booting is actually a fairly hard problem, and (2) the incentive for improving its speed is basically zero in the current desktop OS monopoly environment.

          As far as capacity is concerned, enough is never enough, and folks who've made statements like that have lived to regret th

          • Re: (Score:2)

            by mandolin ( 7248 )
            -- Slow boot: It would be nice if OSes (including Linux) would take more responsibility (I'm aware of upstart and initng). It is a difficult enough problem that the hardware solution may arrive more quickly.

            -- Capacity: In the long term, I agree enough is never enough. For a particular system, I don't think it applies: even an 8GB hard drive connected to an original 8088 IBM PC is wasted (if you could make it work at all). *If* PRAM can scale well enough to stay ahead of "the curve", it will work out. O

  • ...cause they have to push the PRAM a lot...
    • I got modded Redundant for the same joke (although I posted before you) but your wording is actually better than mine.

      Mod parent up.
  • Power consumption specs for programming PRAM are not stated in many places but
    I was able to find a reference here:
    http://www.hitachi.com/New/cnews/051213.html [hitachi.com]

    And for comparison to flash memory, here is the 512Mb 1.8v part from ST Micro:
    http://www.st.com/stonline/products/literature/ds/ 10058/nand512r3a.pdf [st.com]

    The specs do not line up exactly.
    PRAM: 100uA at 1.5V for programming each bit cell
    FLASH: 8ma at 1.8V for programing one page (256 bytes), internally rebuffered in SRAM
  • this was it should be available since it was first invented...

  • Will this be part of the new Camelot architecture?....thought by some to be the "Holy Grail" of computing?

Slashdot Top Deals

He has not acquired a fortune; the fortune has acquired him. -- Bion

Close