Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
Check out the new SourceForge HTML5 internet speed test! No Flash necessary and runs on all devices. ×
Intel Hardware

Why Micron/Intel's New Cross Point Memory Could Virtually Last Forever 179

Lucas123 writes: As they announced their new 3D XPoint memory this week, Micron and Intel talked a lot about its performance being 1,000X that of NAND flash, but what they talked less about was how it also has the potential to have 1,000X the endurance of today's most popular non-volatile memories. NAND flash typically can sustain from 3,000 to 10,000 erase-write cycles — more with wear-leveling and ECC. If Micron and Intel's numbers are to be believed, 3D XPoint could exceed one million write cycles. The reason for that endurance involves the material used to create the XPoint architecture, which neither company will disclose. Unlike NAND flash, cross point resistive memory does not use charge trap technology that wears silicon oxide over time or a typical resistive memory filamentary architecture, which creates a statistical variation in how the filaments form each time you program them; that can slow ReRAM's performance and make it harder to scale. Russ Meyer, Micron's director of process integration, said 3D XPoint's architecture doesn't store electrons or use filaments. "The memory element itself is simply moving between two different resistance states," which means there's virtually no wear.
This discussion has been archived. No new comments can be posted.

Why Micron/Intel's New Cross Point Memory Could Virtually Last Forever

Comments Filter:
  • Wouldn't it be way obsolete by the 1 millionth write cycle ?
    • by delt0r ( 999393 )
      That is the point... practically unlimited read/write cycles.
      • Well, unless you buy into using this technology to fundamentally change how we view memory architecture. I have not done the sums, but I doubt that 1000x NAND's endurance is sufficient for also replacing DRAM.
        • Re:Moor? (Score:5, Funny)

          by delt0r ( 999393 ) on Friday July 31, 2015 @08:14AM (#50222389)
          Even at 1000x faster, i am not sure its fast enough either. But would we ever want persistent ram for everything? I mean how could we turn it off and turn it on again to fix anything ;)
          • by Anonymous Coward on Friday July 31, 2015 @08:22AM (#50222441)

            But a small boot routine in ROM that erases a range of RAM (persistent or not) isn't that hard to conceptualize. Besides, depending on the type of volatile RAM, it doesn't always come up as all zeros at power-on either... I mean, what do you think happens when you press a reset button? Everything is still in RAM at that point.

            What would make things different is a software architecture change that gets rid of the separate permanent storage layer and makes everything RAM-persistent. That would be kinda strange to imagine.

            • What would make things different is a software architecture change that gets rid of the separate permanent storage layer and makes everything RAM-persistent. That would be kinda strange to imagine.

              But isn't the point of restarting the machine to reset it's state? Either from updates or a computer just acting strange?

            • depending on the type of volatile RAM, it doesn't always come up as all zeros at power-on either...

              The original Apple ][ showed this after power up with a screen of random characters, requiring the user to hit the reset key to get things rolling. Fortunately, the reset key was placed conveniently next to the enter key... BEEP!

          • I just want an SSD made with this ASAP. I hope they don't start out at $500 for a 100GB drive.

            • FTA: "It's more expensive than NAND"

            • It's going to cost more than NAND flash.

              But it would make a GREAT cache for spinning rust. None of the longevity problems of NAND, 1,000 times faster. Ka-chow.

              • It's going to cost more than NAND flash.

                But it would make a GREAT cache for spinning rust. None of the longevity problems of NAND, 1,000 times faster. Ka-chow.

                For that matter, it would be a pretty good cache for NAND SSDs. I could do with most of my writes being 1000X faster.

                • This is a good point. If it is significantly more expensive, say 1GB of this as a write buffer on a large SSD drive will make the NAND drive last nearly forever, as frequent writes can be buffered and only written to the nand when necessary. The biggest issue with NAND is when software constantly writes to the disk, and pushes the write wearing logic to the limit.

                  • For serious use, I think 10GB would be better.

                    But even if it started out at 10 x the cost of NAND, a 150GB unit for my databases would definitely be worth it.
              • It's going to cost more than NAND flash ... when introduced

                FTFY

                Once the production scales, the price will drop, and we have no idea how much. At some point, the price will become low enough for "mainstream" consumer products. In the meantime, expect to see this sitting in front of NAND and Spinning Disks on very large SANS as high end CACHE.

              • More importantly, it is byte addressable and doesn't require any of the block erase nonsense of NAND. There is no window during which some (possibly old) data or even the entire device becomes corrupted because of a power loss during a read-modify-(erase)-write cycle. It would be genuinely good if such reliability became a standard feature.

            • Re:Moor? (Score:5, Insightful)

              by Archangel Michael ( 180766 ) on Friday July 31, 2015 @10:00AM (#50223211) Journal

              Here something I learned a while ago; Speed isn't how fast you do something (it is, but only partially), it is often a measure of whether or not you actually CAN do something.

              Here is my story:

              In the Mid 90's I ran an ISP. Part of my daily chores was processing logs looking for anomalies, and to gather stats needed to project out the upgrades that are needed. When I started, the logs were small and it took a few minutes to process. As the business grew, the process took longer and longer. It soon took hours to process the logs for the day. It became so problematic, that I just stopped doing them.

              But business kept growing, and I needed the stats. So, I bought a new machine. The new machine could process the logs in five minutes, what took hours on the older machine. Mind you, this was one generation difference between the two machines (68040 to PPC 701), but that was all that was needed to show me that speed isn't just how long it takes, sometimes it is whether or not you do the thing you ought to do.

              Seeing the price of SSDs and Spinning HD, at their current price points, there is no reason to NOT get the SSD, at whatever cost they are now. Especially for enterprise grade systems that need the IOPS, Even at $1000 for 1 TB SSD is extremely affordable speed, especially when considering you get 90,000 IOPS.

              IF we're talking about 1000x faster, the speed is enough to change what we can do.

          • by Bengie ( 1121981 )
            DDR3 is about 10ns. If XPoint is 1000x faster than 5us NAND, then it has 1/2 the latency of DRAM. I doubt it, but you can see how it can easily be within a a factor or two.

            When you restart your computer without a power down, you still have all that data in memory. Same difference. As for a power down, the only real benefit is it also resets the CPU and other hardware. When the BIOS starts up and copies data from the HD into memory, it already over-writes what was ever there. No changes required. If you wa
        • by sribe ( 304414 )

          Well, unless you buy into using this technology to fundamentally change how we view memory architecture. I have not done the sums, but I doubt that 1000x NAND's endurance is sufficient for also replacing DRAM.

          Doesn't matter anyway. Faster than Flash, but still too slow to replace RAM...

        • I have not done the sums, but I doubt that 1000x NAND's endurance is sufficient for also replacing DRAM.

          No need to do any "math". DRAM is written millions of times per second, this would only last a few seconds as a PC's main data store.

          • by jandrese ( 485 )
            Unless you are doing something weird, a DRAM cell shouldn't be written that hard in typical use. A cell under that much activity should stay in cache.
          • by ACE209 ( 1067276 )
            Isn't that because of the memory refresh, which wouldn't be needed for that kind of memory?
          • Re:Moor? (Score:4, Interesting)

            by Bengie ( 1121981 ) on Friday July 31, 2015 @10:24AM (#50223481)
            Unofficial sources are starting to say that XPoint does not exhibit wear from write cycles and the "1000x more endurance" is normalized to some other metric. If it was normalized against time, then you may expect NAND to last 3-5 years which would put XPoint around 3,000-5,000 years life time. We won't know until more official data or hands-on reviews happen.
        • My guess is that this new technology would fill some spot in the memory hierarchy somewhere between two existing technologies. For example, it might be used between current flash-based SSDs and DRAM to provide persistent memory that's faster than flash (but presumably more expensive) for system startup. Of course, the actual spot in the hierarchy would depend on factors such as speed, endurance, and cost. This is analogous to the fact that many magnetic hard drives now include memory caches.

          Of course, th

          • I've been saying this for a long time. There is a definitive hierarchy between all the different memory locations. Unfortunately we don't have an OS that looks at all these levels as one. We have abstarcted all the CPU Cache, RAM, NAND, Spinning disk, clout etc as separate levels, rather than a single level with varying degrees of capability.

            When we have an OS that can view all the levels as one, intelligently, we'll have a much more efficient OS. It might take a whole new design from the hardware up to acc

      • If information wants to be free, why does my internet connection cost so much?

        Your Internet connection is not information. It is a complex system of wires/tubes/fibers run by computers, and uses electricity, occupies land. It is operated by a corporation who pays people, negotiates with other corporations, and deals with/pays for many subtle and not so subtle political aspects of the whole thing.
      • by Guspaz ( 556486 )

        Practically unlimited? 1000x the endurance of NAND gets you 3 million writes. It's per-byte addressable, and it's supposed to have performance 1000x that of NAND. If you assume NAND has typical access times of 2ms, and then this stuff could write a single byte up to 500,000 times per second.

        In short: without wear levelling, you can burn out this stuff in 6 seconds if you overwrite the same byte as fast as possible.

        If you implement wear levelling on a block level, and use it for storage (and not to replace R

        • by delt0r ( 999393 )
          I have a RAID 0 (faster read whatever mode) SDD hard drive for 2 years not with no problems and i thrash em. If it last 1000x times longer, that is (math in brain, carry the one) 2000 years. Probably good enough for government work.

          Some "how fast can i wreak it" is simply not a relevant metric.
          • by Guspaz ( 556486 )

            It depends on what you're using it for, and how you manage it. Your SSD is doing wear levelling at a block level, but people are talking about using this new stuff to replace RAM. That means per-byte writes (not per-block) with no wear levelling.

      • You do realize that if it is 1000 times as fast, and you can write 1000 times as often, then it will wear out as fast as current SSDs if they are driven equally hard, right?

  • Is this memory based on silicon, or something else, like GaAs or Germanium or Graphene or something else?
    • by arglebargle_xiv ( 2212710 ) on Friday July 31, 2015 @08:27AM (#50222475)

      Is this memory based on silicon, or something else, like GaAs or Germanium or Graphene or something else?

      Given that they've released close to zero technical details on how it works, but stated that it's nonvolatile, has 1000x the endurance of NAND flash while being 1000x faster, is cheaper than DRAM, and will be available in 128GBit capacities any minute now, my guess is that it's based on magic.

      • by theendlessnow ( 516149 ) * on Friday July 31, 2015 @09:30AM (#50222917)

        Given that they've released close to zero technical details on how it works, but stated that it's nonvolatile, has 1000x the endurance of NAND flash while being 1000x faster, is cheaper than DRAM, and will be available in 128GBit capacities any minute now, my guess is that it's based on magic.

        Until they release full specs you cannot assume that it's based on magic. I just hope they didn't base it on myth. But we'll see.

      • by LWATCDR ( 28044 )

        Given that this is Intel and Micron I say bring on the magic. This is not any small startup so I expect to see this very soon.

      • Is this memory based on silicon, or something else, like GaAs or Germanium or Graphene or something else?

        Given that they've released close to zero technical details on how it works, but stated that it's nonvolatile, has 1000x the endurance of NAND flash while being 1000x faster, is cheaper than DRAM, and will be available in 128GBit capacities any minute now, my guess is that it's based on magic.

        Of course it's cheaper than DRAM; DRAM is expensive. TFA says it will be more expensive than NAND and cheaper than DRAM. So, it just adds another point on the continuum... the more speed and write cycles you need, the more it costs. Seems reasonable. And TFA says nothing about availability; not sure where you got that from.

        There's no reason to conclude it's magic. There's also no reason to start designing new architectures around it until we see it in the real world.

    • From the video, it's memristor tech, but everyone is reporting that they are carefully abstaining from letting on what the materials are. Which is fair enough - they want to sew up the market for this stuff as long as possible.

  • long live RM films.
  • by Kythe ( 4779 ) on Friday July 31, 2015 @07:26AM (#50222123)
    I believe they've also indicated the "1000x endurance" figure isn't based upon write cycles -- meaning it has to be based on typical lifetimes. So yes, you're talking many years of service.
    • by Westley ( 99238 )

      At that point, the ability to use this to replace DRAM becomes much more reasonable. If it were really just 1000x the writes of NAND, it would be far too short-lived to act as normal RAM... but if it's *really* the typical lifetime, things could get very interesting indeed...

      • by sribe ( 304414 )

        At that point, the ability to use this to replace DRAM becomes much more reasonable. If it were really just 1000x the writes of NAND, it would be far too short-lived to act as normal RAM... but if it's *really* the typical lifetime, things could get very interesting indeed...

        Nope, worse, not better--the math goes the other way. It's *LESS* than 1000x as many write cycles, but it's 1000x the life cycle in use as non-volatile memory because it can write smaller blocks, thus less write amplification.

      • Contrary to what you believe, its not meant to replace RAM, its meant to replace spinning rust.

        • by epine ( 68316 )

          Contrary to what you believe, its not meant to replace RAM, its meant to replace spinning rust.

          Try turning your technology map right side up.

        • by Bengie ( 1121981 )
          Intel said they're unifying memory and storage with this. No more distinction between DRAM and HDs, they're one and the same. Of course other stuff needs to happen first, but that obviously indicates that they expect it to replace DRAM. Actually, the explicitly stated they will make DRAM with it.
  • Crossbar vs XPoint (Crosspoint) can't wait to see how this plays out.
    Once these hit consumer devices life could be alot faster and last longer :-)
  • Please don't use 'virtually' like that in an article about memory. It's just going to confuse the issue.
  • Physics? (Score:4, Insightful)

    by Lord Duran ( 834815 ) on Friday July 31, 2015 @09:11AM (#50222803)

    Can someone explain how exactly they're "moving between two different resistance states"? Because I think that that in itself does not guarantee lower wear.

    Has anyone heard anything technical about how this works?

  • by Tough Love ( 215404 ) on Friday July 31, 2015 @02:02PM (#50225385)

    If latency is 1,000 times lower and endurance is 1,000 times higher then, under continuous load, endurance measured in real time is unchanged. Not by any means a hypothetical scenario.

Trying to be happy is like trying to build a machine for which the only specification is that it should run noiselessly.

Working...