Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 18 submissions in the queue.
posted by janrinok on Wednesday July 29 2015, @05:21PM   Printer-friendly
from the smaller-yet-bigger dept.

Intel and Micron have announced a new type of non-volatile memory called "3D XPoint", which they say is 1,000 times faster (in terms of latency) than the NAND flash used in solid-state disks, with 1,000 times the endurance. It also has 10 times the density of DRAM. It is a stackable, 20nm, technology, and is expected to be sold next year in a 128 Gb (16 GB) size:

If all goes to plan, the first products to feature 3D XPoint (pronounced cross-point) will go on sale next year. Its price has yet to be announced. Intel is marketing it as the first new class of "mainstream memory" since 1989. Rather than pitch it as a replacement for either flash storage or Ram (random access memory), the company suggests it will be used alongside them to hold certain data "closer" to a processor so that it can be accessed more quickly than before.

[...] 3D XPoint does away with the need to use the transistors at the heart of Nand chips... By contrast, 3D XPoint works by changing the properties of the material that makes up its memory cells to either having a high resistance to electricity to represent a one or a low resistance to represent a zero. The advantage is that each memory cell can be addressed individually, radically speeding things up. An added benefit is that it should last hundreds of times longer than Nand before becoming unreliable.

It is expected to be more expensive than NAND, cheaper than DRAM, and slower than DRAM. If a 16 GB chip is the minimum XPoint offering, it could be used to store an operating system and certain applications for a substantial speedup compared to SSD storage.

This seems likely to beat similar fast and non-volatile "NAND-killers" to market, such as memristors and Crossbar RRAM. Intel and Micron have worked on phase-change memory (PCM) previously, but Intel has denied that XPoint is a PCM, memristor, or spin-transfer torque based technology. The Platform speculates that the next-generation 100+ petaflops supercomputers will utilize XPoint, along with other applications facing memory bottlenecks such as genomics analysis and gaming. The 16 GB chip is a simple 2-layer stack, compared to 32 layers for Samsung's available V-NAND SSDs, so there is enormous potential for capacity growth.

The technology will be sampling later this year to potential customers. Both Micron and Intel will develop their own 3D XPoint products, and will not be licensing the technology.


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 3, Insightful) by VLM on Wednesday July 29 2015, @05:36PM

    by VLM (445) Subscriber Badge on Wednesday July 29 2015, @05:36PM (#215560)

    Wat?

    Intel has denied that XPoint is a ... memristor

    By contrast, 3D XPoint works by changing the properties of the material that makes up its memory cells to either having a high resistance to electricity to represent a one or a low resistance to represent a zero.

    OK, whatever. I'm about to issue a competitor called VLM-emory(tm) that stores ones-n-zeros by changing the electrostatic field between two microscopic parallel plates, but I assure you VLM-emory(tm) isn't a mere dynamic ram cell its totally something new.

    My guess is some patent troll has a patent on "using memristors.... on the internet!" and this is their way of avoiding it.

    Something interesting to think about is if all the specs are true this will rock for stuff like replacing microcontroller static ram, unless by "lasts hundreds of times longer than NAND flash" they mean in the real world "like 10 or so write cycles, probably, and just like NiCad cells we'll blame the end user when they break" Eventually its going to be cheaper to ship billions of bytes of write-mostly-once flash and a register pointer than to ship sram and its backup batteries in a microcontroller.

    You want to think of something weird / mind warping, what happens when immutable/functional programming paradigm hits microcontrollers? Wanna stop wasting battery life changing memory values, well, stop changing them!

    • (Score: 1, Informative) by Anonymous Coward on Wednesday July 29 2015, @06:12PM

      by Anonymous Coward on Wednesday July 29 2015, @06:12PM (#215567)

      Having the resistance of something represent 1/0 doesn't necessarily mean it's a memristor.

      The definition of a memristor is a bit narrower than that despite the patent trolls trying to get it to cover more.
      https://en.wikipedia.org/wiki/Memristor [wikipedia.org]

      And even if it is a memristor I think it's ridiculous if someone could patent and monopolize all memristors. That's as ridiculous as allowing people to patent and monopolize all capacitors.

      • (Score: 2) by maxwell demon on Wednesday July 29 2015, @06:25PM

        by maxwell demon (1608) on Wednesday July 29 2015, @06:25PM (#215572) Journal

        I can assure you, had the capacitor been invented these days, there would be a patent covering all of them. Probably broad enough to also cover rechargeable batteries, if those had not been invented before either.

        --
        The Tao of math: The numbers you can count are not the real numbers.
        • (Score: 2) by Francis on Wednesday July 29 2015, @06:52PM

          by Francis (5544) on Wednesday July 29 2015, @06:52PM (#215578)

          Which is why the funding for the USPTO needs to be increased and provided by the federal government. With application fees being nominal and a large tax on sales of patents.

          • (Score: 1, Interesting) by Anonymous Coward on Wednesday July 29 2015, @08:03PM

            by Anonymous Coward on Wednesday July 29 2015, @08:03PM (#215594)

            Or reduced to zero and the department closed.

            • (Score: 3, Insightful) by Francis on Wednesday July 29 2015, @08:42PM

              by Francis (5544) on Wednesday July 29 2015, @08:42PM (#215601)

              Which worked fine when most inventions required relatively little in the way of resources to produce. These days, the inventions we really need are the ones that require millions of dollars in funding to properly test.

              Take away the USPTO entirely and those innovations won't be coming out of the US at all. I'm all in favor of reform, but burning the building down because the bathroom is dirty doesn't seem terribly practical.

              • (Score: 0) by Anonymous Coward on Thursday July 30 2015, @11:05AM

                by Anonymous Coward on Thursday July 30 2015, @11:05AM (#215829)
                Yeah without all that, Leon Chua wouldn't have thought of the memristor at a major public research university located in Berkeley, California.

                I'm sure the reason people are willing to pay a premium for Apple stuff instead of Korean or Chinese knockoffs is because of all those patents.
                • (Score: 2) by Francis on Thursday July 30 2015, @03:47PM

                  by Francis (5544) on Thursday July 30 2015, @03:47PM (#215911)

                  And where, pray tell, did the funding for his research come from? The university doesn't have huge amounts of money to pay for research, a lot of that money comes from private groups that use royalties to fund the research. No company is going to fund research if the competition can steal the work without consequences.

    • (Score: 2) by captain normal on Wednesday July 29 2015, @06:15PM

      by captain normal (2205) on Wednesday July 29 2015, @06:15PM (#215569)

      Yep, sure looks like dancing around patents to me also. Plus the whole design looks like crossbar switching scheme to me (https://en.wikipedia.org/wiki/Crossbar_switch). Maybe trying to avoid the ancient Bell Labs patents.

      And---"...a 128 Gb (16 GB) size." ? Which is it? From the FA it seems they working with 16 and 32 GB capacity.

      --
      When life isn't going right, go left.
      • (Score: 3, Informative) by gman003 on Wednesday July 29 2015, @06:24PM

        by gman003 (4155) on Wednesday July 29 2015, @06:24PM (#215571)

        128 Gb (gigabits) = 16 GB (gigabytes)

        • (Score: 2) by captain normal on Wednesday July 29 2015, @09:08PM

          by captain normal (2205) on Wednesday July 29 2015, @09:08PM (#215609)

          doh..I didn't see the small "b". My brain only read the Bytes part.

          --
          When life isn't going right, go left.
    • (Score: 0) by Anonymous Coward on Wednesday July 29 2015, @06:56PM

      by Anonymous Coward on Wednesday July 29 2015, @06:56PM (#215579)

      and this is their way of avoiding it.

      I suspect this is tied to the Chinese company 'we want to buy micron'. Micron is coming back with 'uh double that'.

  • (Score: 2) by Runaway1956 on Wednesday July 29 2015, @07:07PM

    by Runaway1956 (2926) Subscriber Badge on Wednesday July 29 2015, @07:07PM (#215581) Journal

    my_entire_operating_system lives on a 30 gig ext4 partition. Only 5.91 gig of that partition is used. 16 gig of memory is a hell of a lot of memory, if you're not running a server. You can create a two gig ram drive for temp and cache, load your most memory intensive game, and I'm pretty certain you can STILL run a couple of virtual machines in the background. Probably still have plenty of spare memory and CPU cycles for distributed computing projects, too. Seriously, the only thing that holds me back on 4 gigs of memory, is the ability to load virtual machines with meaningful memory allocations. (I sure as blazes do NOT want a machine or VM resorting to virtual memory!)

    • (Score: 0) by Anonymous Coward on Wednesday July 29 2015, @07:24PM

      by Anonymous Coward on Wednesday July 29 2015, @07:24PM (#215586)

      yeah. well I do scientific computing. I need RAM.

    • (Score: 3, Interesting) by Aichon on Wednesday July 29 2015, @09:44PM

      by Aichon (5059) on Wednesday July 29 2015, @09:44PM (#215621)

      Yup, 16GB is overkill for many users. And for others, it can be orders of magnitude too small.

      For instance, when I was doing my grad research in 2008, we had a machine with 16GB of RAM, which was quite a bit less than I wanted, given that I was analyzing a 7.8TB data set (representing a web crawl of 6.3B pages, which was at the time the largest in academia) that had been stored as a single file in an undocumented, proprietary format created by an earlier grad student. Oh, and that format couldn't be randomly accessed, meaning that if I wanted to get at a piece of data that was at the end of the 7.8TB file, I'd first have to read in and parse the preceding 7.8TB in order to know which bit the data I was interested in started at. And there wasn't enough space in the RAID to break the file up and store it in chunks.

      It got really bad when they asked me to figure out for each domain which other domains linked to the ones that linked to them (i.e. for a given domain, find the "supporter" domains that linked to the "neighbor" domains that linked to the given one), since the easiest algorithms for that problem assume that you can store the entire data set in memory. Instead, I think we ended up having to design an algorithm that iterated across the entire 7.8TB data set about 500 times (i.e. 7.8TB / 16GB), with each full read of the data taking roughly 4 hours. All of which was quite doable, of course, but it would have been GREATLY simplified if I could have had quite a bit more RAM.

      These days, the only time I tend to have issues on my 8GB machine at home is when doing photo or video editing for fun, which makes sense, since those files can be massive and the professionals in those fields are known for chewing through RAM like nothing else.

      • (Score: 1, Insightful) by Anonymous Coward on Wednesday July 29 2015, @10:21PM

        by Anonymous Coward on Wednesday July 29 2015, @10:21PM (#215635)

        A set of memory mapped files and an index probably would have help you out a decent amount.

        • (Score: 2) by Aichon on Thursday July 30 2015, @02:52PM

          by Aichon (5059) on Thursday July 30 2015, @02:52PM (#215898)

          Agreed, but I was young(er) and didn't know any better. ;)