Slashdot Mirror

← Back to Stories (view on slashdot.org)

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

Posted by samzenpus on from the built-to-last dept.

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.

126 of 179 comments (clear)

  1. Moor? by invictusvoyd · · Score: 1

    Wouldn't it be way obsolete by the 1 millionth write cycle ?

    1. Re:Moor? by delt0r · · Score: 1

      That is the point... practically unlimited read/write cycles.

      --
      If information wants to be free, why does my internet connection cost so much?
    2. Re:Moor? by AikonMGB · · Score: 1

      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.

    3. Re:Moor? by delt0r · · Score: 4, Funny

      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 ;)

      --
      If information wants to be free, why does my internet connection cost so much?
    4. Re:Moor? by The+Real+Dr+John · · Score: 2

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

      --
      A brain is a terrible thing to waste... Mind? That's debatable.
    5. Re:Moor? by sribe · · Score: 1

      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...

    6. Re:Moor? by Joce640k · · Score: 2

      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.

      --
      No sig today...
    7. Re:Moor? by Joce640k · · Score: 1

      FTA: "It's more expensive than NAND"

      --
      No sig today...
    8. Re:Moor? by Dr_Barnowl · · Score: 2

      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.

    9. Re:Moor? by hattig · · Score: 1

      That depends on whether you are using it as storage, or a main memory.

      As a main memory, that is nowhere near enough writes.

      And yes, this is being suggested as a solution for main memories in certain applications. However, these applications will not change state as often - in-memory caches, databases, etc.

    10. Re:Moor? by Marginal+Coward · · Score: 1

      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, the spot in the memory hierarchy could change over time as the parameters of the new memory evolve, notably cost. The new type would only replace some existing memory type when it is better in every way than that type. This happens rarely. For example, the ancient technology of magnetic tape is still with us because of its extremely low cost per byte, which is a compelling feature for certain applications such as archival data storage, despite its long access time.

    11. Re:Moor? by GTRacer · · Score: 3, Funny

      Faster than Flash[...]

      Faster than *THE* FLash? Doubtful. Or did you mean Adobe Flash? That's not much of an achievement.

      --
      Defending IP by destroying access to it? That makes sense, RIAA/MPAA. Go to the corner until you can play nice!
    12. Re:Moor? by swillden · · Score: 2

      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.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    13. Re:Moor? by jandrese · · Score: 1

      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.

      --

      I read the internet for the articles.
    14. Re:Moor? by ACE209 · · Score: 2

      Isn't that because of the memory refresh, which wouldn't be needed for that kind of memory?

      --
      "we are all atheists about most of the gods that societies have ever believed in. Some of us just go one god further."
    15. Re:Moor? by Guspaz · · Score: 2

      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 RAM), then it should be effectively unlimited write cycles.

    16. Re:Moor? by Archangel+Michael · · Score: 4, Insightful

      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.

      --
      Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
    17. Re:Moor? by Archangel+Michael · · Score: 1

      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.

      --
      Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
    18. Re:Moor? by delt0r · · Score: 1

      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.

      --
      If information wants to be free, why does my internet connection cost so much?
    19. Re:Moor? by Archangel+Michael · · Score: 2

      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 accomplish.

      --
      Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
    20. Re:Moor? by ebrandsberg · · Score: 2

      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.

    21. Re:Moor? by Guspaz · · Score: 1

      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.

    22. Re:Moor? by Bengie · · Score: 1

      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 want to take advantage of having persistent memory, then you'll need new protocols, but old protocols should continue to work as expected.

    23. Re:Moor? by Bengie · · Score: 3, Interesting

      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.

    24. Re:Moor? by KingMotley · · Score: 1

      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?

    25. Re:Moor? by Jane+Q.+Public · · Score: 1

      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.

    26. Re:Moor? by KonoWatakushi · · Score: 1

      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.

    27. Re:Moor? by petteyg359 · · Score: 1

      16 times faster is too slow? Basic math, people. DDR-4000 (a.k.a. PC-32000) is 32 GBps. Today's SATA3 SSDs do 500 MBps. 500 MBps times 1000 is 500 GBps, or almost 16 times faster than DDR-4000. If the random hype claims of "1000 times faster" are true, then this kicks the shit out of current RAM.

    28. Re:Moor? by sribe · · Score: 1

      16 times faster is too slow? Basic math, people. DDR-4000 (a.k.a. PC-32000) is 32 GBps. Today's SATA3 SSDs do 500 MBps. 500 MBps times 1000 is 500 GBps, or almost 16 times faster than DDR-4000. If the random hype claims of "1000 times faster" are true, then this kicks the shit out of current RAM.

      They're talking about latency, not bandwidth.

    29. Re:Moor? by Sardaukar86 · · Score: 1

      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?

      Only if you suddenly have a thousand times more work that needs doing.

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

      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.

      I can believe it. Internally it operates like a static ram so there are no need for separate address strobes (although DRAM technically does not need them either) and no precharge.

    31. Re:Moor? by doccus · · Score: 1

      If this gets utilized in SSDs, then I am finally lining up at the door for the first usably big drive.. that being at least a TB

    32. Re:Moor? by petteyg359 · · Score: 1

      Then they should quit using the word "faster", because that doesn't say what they think it does. I could say my 1 Mbps HomePNA network is faster than my 300 Mbps cable internet and everybody would laugh at me because clearly 300 Mbps is faster (even if is has ten times higher latency).

  2. like the lightbulbs that last virtually forever? by Anonymous Coward · · Score: 1, Funny

    The last thing that was supposed to last virtually forever was those overpriced lightbulbs that were supposed to last for decades. I'm lucky if I get a year out of them. Let's revisit the new memory when it has a track record.

  3. Silicon or.... by unixisc · · Score: 1

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

    1. Re:Silicon or.... by arglebargle_xiv · · Score: 4, Funny

      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.

    2. Re:Silicon or.... by Dr_Barnowl · · Score: 1

      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.

    3. Re:Silicon or.... by unixisc · · Score: 1

      Ok, so what are memristors made up of?

    4. Re:Silicon or.... by theendlessnow · · Score: 4, Funny

      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.

    5. Re:Silicon or.... by LWATCDR · · Score: 1

      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.

      --
      See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
    6. Re:Silicon or.... by swillden · · Score: 1

      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.

      --
      Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
    7. Re:Silicon or.... by Bengie · · Score: 1

      "Memristors" are anything with certain meta properties. Assume XPoint fits the theoretical definition of memristor perfectly, you can process and store data at the same time.

    8. Re:Silicon or.... by Codeyman · · Score: 1

      Which is why you'll have to use mana cards to pay for these drives...

    9. Re:Silicon or.... by babybird · · Score: 1

      And TFA says nothing about availability; not sure where you got that from.

      My guess is he got it from Intel's announcement here: http://newsroom.intel.com/comm...

      3D XPoint technology will sample later this year with select customers, and Intel and Micron are developing individual products based on the technology.

      --
      Keith D.
  4. *that* Russ Meyer? by turkeydance · · Score: 1, Insightful

    long live RM films.

    1. Re:*that* Russ Meyer? by justcauseisjustthat · · Score: 1

      Thanks, that name was bugging me :-)

    2. Re:*that* Russ Meyer? by Marginal+Coward · · Score: 1

      So now he's the "director of process integration" at Micron. Looks like he's bustin' out all over. Once a director, always a director, I guess.

    3. Re:*that* Russ Meyer? by jrumney · · Score: 1

      Apparently the working title before his death in 2004 was "Faster Pussycat, Fuck, Fuck", but Micron's marketing department thought XPoint might go over better with the target market.

  5. Endurance figures by Kythe · · Score: 2

    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.

    --

    Kythe
    1. Re:Endurance figures by Westley · · Score: 1

      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...

    2. Re:Endurance figures by sribe · · Score: 2

      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.

    3. Re:Endurance figures by BitZtream · · Score: 2

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

      --
      Persistent Volume manager for Kubernetes - https://github.com/dwimsey/openshift-pvmanager
    4. Re:Endurance figures by NatasRevol · · Score: 1

      The proper question is 'how many zeros is enough'?

      If 10^7 is good for 99% of applications, then it's good enough. And 10^15 is way overkill.

      --
      There are two types of people in the world: Those who crave closure
    5. Re:Endurance figures by epine · · Score: 1

      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.

    6. Re:Endurance figures by Bengie · · Score: 1

      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.

    7. Re:Endurance figures by sribe · · Score: 1

      How is that *worse* than having a lifetime of 1000x the number of write cycles of a NAND drive?

      Because if the write amplification is, for instance, 1/10th that of flash. Then 1000x as many writes would mean 20,000 years.

  6. Re:like the lightbulbs that last virtually forever by Anonymous Coward · · Score: 1

    I've had a couple CFLs go out early, but I do have a few that are going on 7 years, but I've only had one LED bulb die and that was within a week...mfg replaced it. And I'm always a fairly early adopter so my oldest LED bulb is about 4 years old....and yes I paid way to much for it.

    If you are having bad luck, I'm guessing you have crappy power. I'm lucky that my power is pretty clean (I borrowed a powersight monitor from work for a month).

  7. Re:like the lightbulbs that last virtually forever by knightghost · · Score: 3, Informative

    "Crappy power" is normal. Manufacturers need to design for that. How long something lasts in a lab is irrelevant.

  8. Re:Life has taught me by BeerCat · · Score: 2

    that there is always a catch.

    So, what's the catch?

    At the moment - availability.

    Not yet determined - cost

    --
    "She's furniture with a pulse"
  9. Is this phase change memory? by Anonymous Coward · · Score: 1

    This sounds like this may be some sort of phase change memory where controlled pulses of current can switch a material between a high and low resistance phase. The memory can then be read by passing low current through the bit to determine which phase it is in without flipping the phase.

    1. Re:Is this phase change memory? by Bengie · · Score: 1
      Nope, not phase change. According to Intel XPoint doesn't have any physical changes, only property changes. Some people mentioned electron spins.
      Wiki

      the fact that phase-change is a thermally driven process

  10. Crossbar vs XPoint (Crosspoint) by justcauseisjustthat · · Score: 1

    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 :-)

  11. Remanance properties? by SlideRuleGuy · · Score: 1

    But what is its behavior re data remanance? Not the first concern of course, but certainly one of them these days...

    1. Re:Remanance properties? by Guspaz · · Score: 1

      Has anybody actually ever demonstrated recovery of overwritten data in the real world (as opposed to the lab) on either HDDs or SSDs?

  12. Not nearly forever by spirtbrat · · Score: 1

    Wear-leveling, levels the demand for erase-write a cell, between all available cells. It does not increase their durability. It just makes them equally worn out, so part of them don't fail, while the others still have a lot of juice in them. ECC catches errors caused by the environment. It also does not increase the durability limit of the cells. And after they're worn out - they are worn out. ECC will not make them continue to store info for you. 8GB x 1million write cycles = 8 000 000 GB changed. According to Wikipedia, DDR3-1600 has a Peak transfer rate of 12,5GB/s. At comparable speeds, the 8GB of Intel's new memory will be worn out in about 178h, which is a little over a week of crunch. And this is not nearly forever.

    1. Re:Not nearly forever by newslash.formatblows · · Score: 1

      Aren't you assuming that all of that RAM is being changed as fast as possible, around the clock? No idea how to get a better estimate, but I can't really believe my PC's DRAM is working full-out nonstop at all times.

    2. Re:Not nearly forever by spirtbrat · · Score: 1

      Your RAM directly modifies the specific parts your program need modified. On the other hand, if your SSD did the same, these parts will wear out quicker than the others, so the SSD only says that it modifies the same address, but it actually has its own controller which makes things so a different cell is modified each time (in the ideal case) - that's called "wear-leveling". If Intel's gizmo is prone to such wear, it most probably will use some sort of wear-leveling too. This makes the whole device wear out almost evenly with the speed of memory change. You are right that working with the memory doesn't include only writes. There are a lot of reads too and the reads aren't causing wear. So, if reads:writes are 4:1, then you are looking at a month, instead of a week. This again is short of 'nearly forever'.

    3. Re:Not nearly forever by ezakimak · · Score: 1

      Yes, but this technology does not need any refresh cycles--so the only changes it would incur are actual data value changes. But the point still stands, RAM access in typical high-load server process is going incur lots of changes--too many even for this technology to touch as a viable replacement even without refresh cycles.

    4. Re:Not nearly forever by gweihir · · Score: 1

      That depends very much on what your PC is doing. Some workloads write a lot to RAM.

      --
      Most ACs are not even worth the keystrokes to insult them. Be generically insulted by this and ignored otherwise.
    5. Re:Not nearly forever by ChrisMaple · · Score: 1

      Refresh rate is much lower than maximum data rate.

      --
      Contribute to civilization: ari.aynrand.org/donate
  13. OT: sig reply by NotQuiteReal · · Score: 2

    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.

    --
    This issue is a bit more complicated than you think.
    1. Re:OT: sig reply by delt0r · · Score: 2

      Woosh.....

      --
      If information wants to be free, why does my internet connection cost so much?
    2. Re:OT: sig reply by HornWumpus · · Score: 1

      Whoosh implies funny...

      --
      John McAfee 'It was like that time I hired that Bangkok prostitute; to do my taxes, while I fucked my accountant'
    3. Re:OT: sig reply by delt0r · · Score: 1

      No it doesn;t. It implies you missed tone and meaning.

      --
      If information wants to be free, why does my internet connection cost so much?
  14. I know this is funny to laugh about... by Anonymous Coward · · Score: 4, Informative

    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.

    1. Re:I know this is funny to laugh about... by acoustix · · Score: 1

      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?

      --
      "A plan fiendishly clever in its intricacies"- Homer Simpson
    2. Re:I know this is funny to laugh about... by Sponge+Bath · · Score: 1

      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!

  15. Physics and economics don't care by sjbe · · Score: 4, Insightful

    "Crappy power" is normal. Manufacturers need to design for that.

    Yeah, see physics doesn't care what you think is "normal". While it's possible to design for a reasonable range of power conditions it is not economically possible to design for all of them. Frankly if your power quality is so poor that they are constantly blowing out light bulbs the answer is to fix the power, not the bulbs. You take the bullets out of the gun rather than insist everyone wear a bullet proof vest.

    1. Re:Physics and economics don't care by CODiNE · · Score: 2

      Now why should he have to pay $500 to fix his power problems when he can demand Intel and Micron spend $500M to fix it for him?

      --
      Cwm, fjord-bank glyphs vext quiz
    2. Re:Physics and economics don't care by sd4f · · Score: 1

      Economics only matter when they factor in planned obsolescence. The reality is, the cost to make the design that little bit better than the specifications call for, is usually not that big a factor because, invariably it's just a material cost. Yes there will be exceptions, but for a lot of electronic devices, like say an incandescent light bulb, well, they could make the filament better rated, but, if they did that, then light bulbs wouldn't have failed, and people wouldn't keep having to replace them.

    3. Re:Physics and economics don't care by ChrisMaple · · Score: 1

      Most people aren't stupid about light bulbs, including not being stupid enough to buy your conspiracy theory about filament life. Long life incandescent lights are available, giving 2X or 4X life. The problem is that there's an unavoidable tradeoff; long-life bulbs are less efficient, so much less efficient that even including purchase price the long-life bulbs give less light per dollar.

      --
      Contribute to civilization: ari.aynrand.org/donate
    4. Re:Physics and economics don't care by localman · · Score: 2

      > You take the bullets out of the gun rather than insist everyone wear a bullet proof vest.

      Whoa whoa whoa. What country do you live in?

    5. Re:Physics and economics don't care by Bob+the+Super+Hamste · · Score: 2

      I looked into long life incandescent bulbs for my car since I hate replacing them (who has hands that dainty), then I just said fuck it and bought some LED ones as they last much longer than even the long life incandescent ones and are brighter than the regular incandescent ones.

      --
      Time to offend someone
    6. Re:Physics and economics don't care by rubycodez · · Score: 1

      do tell the $500 solution that would "fix the power" for an entire house.

    7. Re:Physics and economics don't care by Raenex · · Score: 1

      said fuck it and bought some LED ones as they last much longer than even the long life incandescent ones and are brighter than the regular incandescent ones

      Yup, way too bright. As a driver caught in those lights, I hate the new LED headlights.

    8. Re:Physics and economics don't care by Raenex · · Score: 1

      Troll country.

    9. Re:Physics and economics don't care by sd4f · · Score: 1

      Well, I probably shouldn't have spoken about incandescent bulbs (although the phoebus cartel does seem a little suspect), but I worked at a heating element manufacturer, and we made elements with no consideration to limiting life at all. As a result, we had elements in processes that were lasting well beyond 30 years. This couldn't be compared with competitors elements, who we were continually replacing. Heating elements essentially work in a very similar manner to an incandescent light bulb.

      Then you consider planned obsolescence in many other devices. If you ever compare electric motors for domestic applications, to proper commercial applications (and I'm not talking about something with a label saying 'Heavy Duty'), you'll know what I mean, they're chalk and cheese between the two.

    10. Re:Physics and economics don't care by Bob+the+Super+Hamste · · Score: 1

      These weren't replacements for the headlights as there really aren't any good LED replacements for the old H11 or H7 bulbs as the LED replacements for them are actually much dimmer. While I could go through and do an expensive silly upgrade to aftermarket LED headlight assemblies I don't want to sink about $1000 into something that provides no real value. I was talking about replacing the various tail and indicator lights which are small cheap, and won't blind people.

      --
      Time to offend someone
  16. Virtual Memory by Translation+Error · · Score: 1

    Please don't use 'virtually' like that in an article about memory. It's just going to confuse the issue.

    --
    When someone says, "Any fool can see ..." they're usually exactly right.
  17. Re:like the lightbulbs that last virtually forever by Applehu+Akbar · · Score: 2

    ""Crappy power" is normal. Manufacturers need to design for that. "

    Get a UPS.

  18. Re:Life has taught me by Dr_Barnowl · · Score: 1

    Cost : "between NAND and DRAM."

    Even if it was cheaper to fab right now than NAND, they wouldn't admit it, because they'd be less able to charge a premium price for it. I'm betting that since it has a higher density than NAND and a simpler construction, it will probably end up cheaper than NAND in the longer run.

    And DRAM is horribly expensive to fab. So "cheaper than DRAM" leaves a large window.

    Right now they are pitching it at the enterprise storage market but that's only smart business - while they ramp up production capacity, get the highest price for it you can.

  19. Re:Life has taught me by TheDarkMaster · · Score: 1

    Will only be available in ten years, like all other revolutionary technologies that are advertising for some time.

    --
    Religion: The greatest weapon of mass destruction of all time
  20. Re: like the lightbulbs that last virtually foreve by ChrisMaple · · Score: 1, Informative

    If it was ever true that power cycling is hard on incandescents, it hasn't been for decades. The primary wearout mechanism is evaporation of the filament.

    --
    Contribute to civilization: ari.aynrand.org/donate
  21. Physics? by Lord+Duran · · Score: 3, Insightful

    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?

    1. Re:Physics? by mr_mischief · · Score: 1

      My guess, and it's only a guess, is the Mott transition.

    2. Re:Physics? by MatthiasF · · Score: 1

      Phase change is my guess.

      Some of the first Memristor are based on phase changing of a material that causes the resistance to adjust with the data.
      https://en.wikipedia.org/wiki/...

      Samsung produced a test cell back in 2006 that showed promise, maybe the medium is finally reaching reliable yield and capacity density to compete with NAND and NOR.

      https://en.wikipedia.org/wiki/...

    3. Re:Physics? by rubycodez · · Score: 1

      Don't know of any Mott transitions except by pressure, temperature or doping though

    4. Re:Physics? by mr_mischief · · Score: 1

      This is all wild speculation, of course. My actual guess is it's some phase change different from what's commonly used in PCM. They've specifically stated it's not PCM, memristors, or filaments. That honestly doesn't leave too many semiconductor transitions for it to be. It leaves even fewer that would be non-volatile in the absence of a maintenance voltage. Maybe it changes crystalline structure from one form to another or changes crystal alignment without ever becoming fully liquid or gaseous.

  22. Re:Call me cynical by thegarbz · · Score: 1

    Care to give examples of when a company which spends the GDP of a small country on R&D has ever overhyped technology or not delivered a product?

    This isn't some silicon valley startup, or some small PhD student turned patent holder hiding in some dingy lab at a university we're talking about.

  23. Re:like the lightbulbs that last virtually forever by drinkypoo · · Score: 1

    "Crappy power" is normal. Manufacturers need to design for that.

    No, you need to design for that. Install a power conditioner, or a UPS (not SPS). You can fix this problem.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  24. Re:like the lightbulbs that last virtually forever by thegarbz · · Score: 1

    The last thing that was supposed to last virtually forever was those overpriced lightbulbs that were supposed to last for decades. I'm lucky if I get a year out of them.

    Don't buy overpriced and overhyped. Just buy good quality. There's no reason you should have failing lightbulbs anymore unless you're driving them with really nasty power or installing them in some wonderfully heat-trapping light fittings.

  25. Re: like the lightbulbs that last virtually foreve by drinkypoo · · Score: 1

    I think people notice incandescents fail right when being turned on rather than just crapping out while they were already running. I don't know if this is selection bias and these events are just more noticable than the other types of failure.

    I'm quite sure that they fail right when turned on more in this house, but I've got almost all of them replaced with Cree lights now that they are dirt cheap at the home despot. Except I've got a $1 CFL over the stove, where the most lights died, and it's been a peach.

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  26. Re:like the lightbulbs that last virtually forever by thegarbz · · Score: 1

    "Crappy power" is not normal. Many western power grids have strict standards for voltage spikes, dips, sags, frequency errors, and THD that they will provide you. If you have crappy power it's because either your wiring is stuffed or you're running devices which are absolutely ancient (30 year old fridges make for some nasty power spikes), or have electronics which are failing / fake / never had the right certification to begin with and are spewing noise back onto your powerline.

  27. Re:like the lightbulbs that last virtually forever by hendrips · · Score: 1

    It is? I'm genuinely curious why you say that. My impression is that in the developed world the power supply is quite reliable and carefully regulated, and that even in the less-developed parts of the world, you can find relatively inexpensive solutions for normalizing your home power, if it's that important.

  28. Re:like the lightbulbs that last virtually forever by Guspaz · · Score: 1

    I've got a whole whackload of Cree LED bulbs. I had a 100W completely die, my other 100W flashes on occasion (apparently their 100W bulbs have a notoriously high failure rate), I had to get rid of a 60W from a lamp fixture because it periodically switched back and forth between full brightness and lower brightness. So far, they have not been substantially more reliable than CFL or incandescent. They may not burn out as often, but they "soft-fail" more often than CFL or incandescent did, those tended to either work fine or not at all.

    Their warranty is basically worthless. They are only sold by one store (Home Depot), and warranty replacements can't be done where you bought it. You need to ship them the broken lightbulb (at your own cost) to get a replacement, and shipping something that size/weight costs more than buying a new LED bulb in the first place, making the warranty completely useless.

  29. Re:like the lightbulbs that last virtually forever by hendrips · · Score: 1

    I was not aware that LED light bulbs have been having significant problems (those are the only types of bulbs I can think of that are supposed to "last for decades," correct me if I'm misunderstanding). My impression is that LED bulbs are improving in longevity and dropping in price very rapidly. If we're just trading anecdotes, I have not had to replace a single LED bulb at my house since I started phasing them in 6 years ago.

  30. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  31. Re:Memristor? by Anubis+IV · · Score: 1

    I saw comments elsewhere that indicated Intel has denied that this is a memristor. Of course, given the description they're providing of what this thing is, it's possible they're just saying that in order to try and avoid the inevitable patent lawsuits that would result from claiming they're using a memristor.

  32. Re:Life has taught me by Archangel+Michael · · Score: 1

    IF it was cheaper (or even close) to manufacture than NAND, then they ought to forgo profits and gain Marketshare and put the NAND business out. They would make more money in the long run. This is unique process, nobody else has, Marketshare means long term (this is electronics, which means 7 years max) profitability.

    I can see charging a premium for early (beta) testers, and as they iron out the bugs (there will be a bunch) but as they ramp up production, the cost WILL come down, quickly.

    If I were in the market for faster more durable short range data storage, I would be a heavy better and get in on early adoption, just so I can see what it can do and how useful it could be.

    --
    Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
  33. Re:Call me cynical by TwoEyedJack · · Score: 1

    Care to give examples of when a company which spends the GDP of a small country on R&D has ever overhyped technology or not delivered a product?

    This isn't some silicon valley startup, or some small PhD student turned patent holder hiding in some dingy lab at a university we're talking about.

    Cypress wasted a billion on developing MRAM. Not that Cypress can be considered in the same category as Micron/Intel.

  34. Re:Call me cynical by jones_supa · · Score: 1

    Care to give examples of when a company which spends the GDP of a small country on R&D has ever overhyped technology or not delivered a product?

    Sure. How about the Archival Disc?

  35. Re:like the lightbulbs that last virtually forever by Bob+the+Super+Hamste · · Score: 1

    I blame children. A couple of years ago mine discovered that if you flip the switch up and down fast you get a strobe effect. It sort of works with CFLs but it does end their life pretty quick. Previous to that I think I had replaced 1 CFL bulb in the bathroom in the previous 7 years. Also the quickest way for them to quit doing that is to make them pay for a new bulb and tell them they can do it some more but they get to keep buying bulbs.

    --
    Time to offend someone
  36. Re:like the lightbulbs that last virtually forever by rubycodez · · Score: 1

    the 40W and 60W equivalent I've had no issues with, has anyone tried the 75W equivalent.

    Maybe 100W equivalent (13.5 watts) is just too much heat in too small an area for LEDs

  37. Re:Call me cynical by rubycodez · · Score: 1

    Madshrimps overclocked a Netburst Celeron 352 to 8,1 GHz in liquid nitrogen. With air cooling they did 5.7 GHz

  38. Re:Call me cynical by Bengie · · Score: 1

    10ghz is what they predicted, XPoint already exists.

  39. Re:Memristor? by Bengie · · Score: 1

    Memristor is an a pseudo-object with a set of meta properties. A lot of things could be technically be a memristor. Human skin can technically be one, but making use of it would be rather difficult. XPoint may be similar to a memristor in a layman's sense, but Intel may realize that XPoint only has the property of storage, which is not the only meta property required. It is also not phase-change because nothing physical changes. Not much information to go on.

    The only thing for sure is it is a form of ReRAM.

  40. Re: like the lightbulbs that last virtually foreve by Blaskowicz · · Score: 1

    I even had an incandescent explode (or more accurately implode) when turning it on.

  41. Re:like the lightbulbs that last virtually forever by Moridineas · · Score: 1

    I had three of the 40w TW Cree bulbs crap out with flickering and eventually dying. I contacted Cree support, took a photo of the packaging, and they, no questions asked, fedexed me three new bulbs. I didn't have to send the old ones back. Worth a shot.

  42. Real time endurance stays the same by Tough+Love · · Score: 2

    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.

    --
    When all you have is a hammer, every problem starts to look like a thumb.
  43. Re:1 Million write-cycles is available in Flash by Tough+Love · · Score: 1

    whatever, we have terabyte hard drives now, so it's pointless to resurrect this technology.

    Where is your exabyte drive going to come from?

    --
    When all you have is a hammer, every problem starts to look like a thumb.
  44. Re:Call me cynical by thegarbz · · Score: 1

    Still waiting on that 10GHz Pentium 4 that Intel promised me. Or rather, that they bragged the NetBurst architecture would be able to hit.

    And I'm sure they would have hit it too if the world didn't turn around and say stop this is absurd your pipelines are getting too long, your processors are getting to hot and we're going to shop at your competitor who's chasing efficiency rather than pointless speed.

    NetBurst was a delivered architecture.

    Some people got quite close to 10GHz using incredible cooling and overclocking techniques.

    Next.

  45. Re:Call me cynical by thegarbz · · Score: 1

    The Blu-ray went from concept to product in 3 years and the specification only took an additional year on top of that. So 4 years to develop.

    The CD took 3 years from joining of efforts between Sony and Philips, 2 years from the time the Redbook standard was published, and that's not taking into account that both companies had been working independently prior to 1979.

    Given we're only 1 year into the Archival Disc announcement I'll give them a little more time before I declare it vaporware.

  46. Re:like the lightbulbs that last virtually forever by thegarbz · · Score: 1

    I've been in my house 5 years and replaced one. It broke when I knocked a lamp over.

    So... back to either finding a decent bulb fittings which don't overheat the bulb or getting the power quality in your house checked.

  47. Re: Call me cynical by Guspaz · · Score: 1

    Of course I do, IPC has also improved significantly since then. I'm merely disputing the claim that Intel has never "overhyped technology" or "not delivered a product".

    They overhyped the P4, and did not deliver on their promise of a 10GHz P4.

    Intel has a lot of great products, but the assertion that thegarbz made was absurd.

  48. Re:like the lightbulbs that last virtually forever by Agripa · · Score: 1

    "Crappy power" is not normal. Many western power grids have strict standards for voltage spikes, dips, sags, frequency errors, and THD that they will provide you. If you have crappy power it's because either your wiring is stuffed or you're running devices which are absolutely ancient (30 year old fridges make for some nasty power spikes), or have electronics which are failing / fake / never had the right certification to begin with and are spewing noise back onto your powerline.

    - standards are great. You know what is greater though? How often are the standards met. Get back to us with metrics or you are talking about "in a perfect world...";
    - lightning. 'Nuff said;

    Which sums up were I live about 30 minutes west of St. Louis, Missouri. We get regular thunderstorms and lose power 2 or 3 times a year for hours and probably twice that often for seconds to minutes every year. Light bulbs including incandescent, compact florescent, and LED have half lives here of 3 to 6 months so the later two are not even close to economical no matter how much more efficient they are.

    All of my computers, network gear, and test equipment is protected by online UPSes which has worked out well.

  49. Re:Fix the Power by rubycodez · · Score: 1

    Nice, that would do the computer gear and lights, but not the kitchen and HVAC and then women's hair dryers (wife and daughter should go solar for that, as in stand outdoors)