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 martyb on Friday August 21 2015, @11:31AM   Printer-friendly
from the waiting-for-"Optene"-or-maybe-"Optyne" dept.

Were you concerned that Intel and Micron's new and totally-not-phase-change-memory technology would become vaporware? At the Intel Developer Forum 2015, Intel announced that 3D XPoint based products will be available in 2016 under a new brand name: Optane.

The Optane products will be available in 2016, in both standard SSD (PCIe) form factors for everything from Ultrabooks to servers, and in a DIMM form factor for Xeon systems for even greater bandwidth and lower latencies. As expected, Intel will be providing storage controllers optimized for the 3D XPoint memory, though no further details on that subject matter were provided. This announcement is in-line with Intel and Micron's original 3D XPoint announcement last month, which also announced that 3D XPoint would be out in 2016.

Finally, as part of the Optane announcement, Intel also gave the world's first live 3D XPoint demonstration. In a system with an Optane PCIe SSD, Intel ran a quick set of live IOps benchmarks comparing the Optane SSD to their high-end P3700 SSD. The Optane SSD offered better than 5x the IOps of the P3700 SSD, with that lead growing to more than 7x at a queue depth of 1, a client-like workload where massive arrays of NAND like the P3700 traditionally struggle to achieve maximum performance.


Original Submission

Related Stories

Intel and Micron Announce 3D XPoint, A New Type of Memory and Storage 17 comments

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

SanDisk and HP Announce Potential Competitor to XPoint Memory 5 comments

HP and SanDisk have announced the development of Storage-Class Memory, a technology with attributes similar to Intel and Micron's 3D XPoint ("crosspoint") memory:

HP and SanDisk are joining forces to combat the Intel/Micron 3D XPoint memory threat, and developing their own Storage-Class Memory (SCM) technology.

SCM is persistent memory that runs at DRAM or near-DRAM speed but is less costly, enabling in-memory computing without any overhead of writing to slower persistent data storage such as flash or disk through a CPU cycle-gobbling IO stack. It requires both hardware and software developments. Micron and Intel's XPoint memory is claimed to be 1,000 times faster than flash with up to 1,000 times flash's endurance. Oddly enough HP and SanDisk say their SCM technology is also "expected to be up to 1,000 times faster than flash storage and offer up to 1,000 times more endurance than flash storage."

[...] The partnership's aim is to create enterprise-class products for Memory-driven Computing and also to build better data centre SSDs. The Storage-Class Memory deal is more long-term: "Our partnership to collaborate on new SCM technology solutions is expected to revolutionise computing in the years ahead."

[...] It's not yet known what the XPoint cell process is, beyond being told it's a bulk change to the material but not a phase-change. Analyst Jim Handy has written an XPoint report which said HP had abandoned its Memristor technology. This SanDisk partnership implies that this point is incorrect.

The HP/SanDisk duo also intend to contribute to HP's Machine concept, "which reinvents the fundamental architecture of computers to enable a quantum leap in performance and efficiency, while lowering costs and improving security."

As we previously reported, Intel and Micron plan to release SSD and DIMM XPoint-based products in 2016, with Intel marketing them under the brand name "Optane".

Is HP's memristor partnership with Hynix obsolete? Will HP Enterprise finally give birth to "The Machine" and change supercomputing? Will Crossbar's ReRAM wither and die, or will the company join the fray and compete to produce the ultimate post-NAND memory?


Original Submission

Intel 3D XPoint... Still Coming Soon 8 comments

Some of Lenovo's new laptops will ship with Intel's 3D XPoint ("Optane"-branded) SSDs, an alternative to NAND flash and RAM. However, they may not arrive by Q1 2017 and the capacities are still small:

Lenovo's announcement today of a new generation of ThinkPads based on Intel's Kaby Lake platform includes brief but tantalizing mention of Optane, Intel's brand for devices using the 3D XPoint non-volatile memory technology they co-developed with Micron. Lenovo's new ThinkPads and competing high-end Kaby Lake systems will likely be the first appearance of 3D XPoint memory in the consumer PC market.

Several of Lenovo's newly announced ThinkPads will offer 16GB Optane SSDs in M.2 2242 form factor paired with hard drives as an alternative to a using a single NVMe SSD with NAND flash memory (usually TLC NAND, with a portion used as SLC cache). The new Intel Optane devices mentioned by Lenovo are most likely the codenamed Stony Beach NVMe PCIe 3 x2 drives that were featured in roadmap leaked back in July. More recent leaks have indicated that these will be branded as the Intel Optane Memory 8000p series, with a 32GB capacity in addition to the 16GB Lenovo will be using. Since Intel's 3D XPoint memory is being manufactured as a two-layer 128Gb (16GB) die, these Optane products will require just one or two dies and will have no trouble fitting on to a short M.2 2242 card alongside a controller chip.

The new generation of ThinkPads will be hitting the market in January and February 2017, but Lenovo and Intel haven't indicated when the configurations with Optane will be available. Other sources in the industry are telling us that Optane is still suffering from delays, so while we hope to see a working demo at CES, the Optane-equipped notebooks may not actually launch until much later in the year. We also expect the bulk of the initial supply of 3D XPoint memory to go to the enterprise market, just like virtually all of Intel and Micron's 3D MLC NAND output has been used for enterprise SSDs so far.

Phoenix666 points out:

When it ships in March, the T570 will be ready to run Intel's Optane, a new class of memory and storage that promises to be significantly faster than today's SSDs and DRAM.

The T570 is the first laptop announced with support for Optane. Intel has not said when it will ship Optane memory, but the T570 has the hooks to support the technology.

Previously: Intel and Micron Announce 3D XPoint, A New Type of Memory and Storage
False News: Intel Announces "Optane"-Brand 3D XPoint SSDs and DIMMs for 2016


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: -1, Troll) by Anonymous Coward on Friday August 21 2015, @12:01PM

    by Anonymous Coward on Friday August 21 2015, @12:01PM (#225793)

    Sell crap to idiots, faster.

  • (Score: 4, Funny) by meisterister on Friday August 21 2015, @12:52PM

    by meisterister (949) on Friday August 21 2015, @12:52PM (#225808) Journal

    This sounds like someone choking as they try to say "opteron" at a car show.

    --
    (May or may not have been) Posted from my K6-2, Athlon XP, or Pentium I/II/III.
  • (Score: 0) by Anonymous Coward on Friday August 21 2015, @12:54PM

    by Anonymous Coward on Friday August 21 2015, @12:54PM (#225810)

    As much as I'd like to get excited about new tech deep down I know it will be years before I can actually afford it. By my count it took 5 years before I could afford[and trust] a decent SSD.

    • (Score: 0) by Anonymous Coward on Friday August 21 2015, @02:08PM

      by Anonymous Coward on Friday August 21 2015, @02:08PM (#225844)

      I am with you.

      These releases are currently vaporware. They have very deliberately NOT given sizes. Just generalizations of what it might do. I was very excited at first but now not so much.

      If they can do half of what they are speculating then these will be interesting. But does not look like they are positioning it as a flash replacement but a flash cache and handheld device memory BOM cost reducer.

      It is interesting that they are putting it near the memory subsystem using DIMM packaging. Which says they see it more as a memory subsystem replacement.

      I said it before and I say it again. The split comparison of speed vs SSD and size vs memory is kinda misleading. They are trying to imply it is both. When we do not see speed vs memory and size vs SSD.

      I could just be paranoid. But it is at least still pretty cool stuff.

    • (Score: 2) by Runaway1956 on Friday August 21 2015, @06:37PM

      by Runaway1956 (2926) Subscriber Badge on Friday August 21 2015, @06:37PM (#225970) Journal

      I'd have to buy a new computer anyway. I have two PCIe x8 slots (PCIe 2), and one of those it the video card. No way am I going back to lame onboard video, and my double-width video dictates that I can't plug anything else into the other PCIe slot. Ehhh - expect to see motherboards in the not-distant future with zero PCI slots, and six or more PCIe.

      Besides which, these things will probably require PCIe x16 - no good on this board! Even using a riser, the disks would communicate at 8x instead of 16x.

  • (Score: 0) by Anonymous Coward on Friday August 21 2015, @12:56PM

    by Anonymous Coward on Friday August 21 2015, @12:56PM (#225812)

    how many GT/sec will the CPU (and chipset?) need to have if you want to use TWO of these?

    • (Score: 0) by Anonymous Coward on Friday August 21 2015, @12:58PM

      by Anonymous Coward on Friday August 21 2015, @12:58PM (#225813)

      you mean, like did the article mention the test setup, thus revealing the GT/sec capabilities of the CPU used in obtaining : ) these IOPS results?
      no.

  • (Score: 0) by Anonymous Coward on Friday August 21 2015, @01:09PM

    by Anonymous Coward on Friday August 21 2015, @01:09PM (#225818)

    in soviet russia beowulf cluster optains you!

  • (Score: 0) by Anonymous Coward on Friday August 21 2015, @01:22PM

    by Anonymous Coward on Friday August 21 2015, @01:22PM (#225823)

    I am having a hard time believing that a massive array of solid state memory has a hard time accessing a single thing at a time.

    This seems like a very cherry picked result.

    My business provided encrypted traditional hard disk drive with platters -- is constantly at 100% activity with queue depths exceeding 14, sometimes beyond 25 -- simply because of everything going on and how much is accessed concurrently (the cloud makes it worse... slow to get and slow to cache).

    If I had a queue depth of 1, I wouldn't be complaining to them I want even the cheapest SSD available. A queue depth of one is simplistic.

    I suppose having dozens of drives in a RAID of some kind (or however the stacking is done inside a single drive) could lead to situations where that 4kb text file really isn't spread across all of the memory and thus isn't accessed concurrently by each memory stack/node in a raid leading to a totally awesome read speed, but I think the one drive or chip that finds it won't have a problem delivering it to me -- even if it's rated at the speed of just one chip, and not many.

    That isn't a failure, that's reality, and that isn't a struggle with performance on a traditional client work load.

    Anyway, if this is to be a Xeon system storage, then why are they testing client-like workloads with a queue depth of 1, anyway. That isn't what those servers will be doing -- they'll be doing that dozens or hundreds of times servicing many clients demanding that data so they can do their own client workload of 1 with the delivered data.

    • (Score: 3, Informative) by gman003 on Friday August 21 2015, @01:52PM

      by gman003 (4155) on Friday August 21 2015, @01:52PM (#225835)

      It's precisely because flash SSDs use massive arrays of memory that they scale better with higher queue depths, because they can perform multiple requests in parallel.

      Most modern, consumer-level SSD controllers are eight-channel designs (server-level controllers have more channels, eg. Intel's top controller is a fourteen-channel architecture). Eight requests that go to memory on a different channel can be served in parallel. Contrast a hard drive, which can only serve a single request at a time.

      • (Score: 0) by Anonymous Coward on Friday August 21 2015, @02:10PM

        by Anonymous Coward on Friday August 21 2015, @02:10PM (#225845)

        I agree with everything you said -- do you think their benchmark was appropriate, though?

        It seems like they are doing a benchmark on "server" hardware, that is baselined against some sort of client workstation hardware in a vacuum with a spinning disk with a queue depth of one and a workload with a queue depth of one.

        Synthetic benchmarks being what they are and that's what sort of scores we'll get -- I think we all believe that there are better synthetic benchmarks reflecting difficult enterprise workloads to choose from, and they chose the one that seemed to be someone doing a single task on a desktop, and then stated it was hard to match.

        I don't disagree that it can be hard to read a single queue depth across multiple devices -- be them SSD or traditional disk arrays -- but the workload in place on the existing hardware that would get replaced by this product -- would rarely ever be doing that.

        It reminds me of the type of marketing that states that this vitamin is 50x more anti-oxidant capable than some other vitamin. Ok, how many do anti-oxidant units do I need, and if its a nutrient, what if I needed a different nutrient? Vitamin E doesn't cure scurvy despite being 50x more anti-oxidant in some capacity. But only a small amount of Vitamin C will prevent scurvy.

        How many performance improvements for single queue depth do we need, if the workload is mostly multiple queue depths?

        The improvement is great, sure... but I am not convinced that it's relevant to their specific claims for their target audiences.

        But what do I know, I am an anonymous coward!

        • (Score: 3, Interesting) by gman003 on Friday August 21 2015, @02:45PM

          by gman003 (4155) on Friday August 21 2015, @02:45PM (#225871)

          If you look at their actual presentation, they ran benchmarks at various queue depths, not just QD1. QD1 merely had the highest split between flash and xpoint. Both scale to higher queue depths, but xpoint is held back less by low queue depths.

          I agree that QD1 isn't particularly relevant for servers, but they're targeting it at all market segments. Servers are merely the most likely place for it to be quickly adopted, but they want it in everything from laptops on up.

  • (Score: 2, Informative) by ese002 on Friday August 21 2015, @06:17PM

    by ese002 (5306) on Friday August 21 2015, @06:17PM (#225965)

    Good luck using those these DIMMS in your AMD box or ARM server. They are non-standard [eetimes.com]

  • (Score: 2) by Gravis on Saturday August 22 2015, @05:36AM

    by Gravis (4596) on Saturday August 22 2015, @05:36AM (#226155)

    while yes, intel may be first to market, they are leveraging this memory to force people to keep buying there processors. i would rather wait a few years for the phase-change-memory-that-they-swear-this-isn't to hit the market than reward intel for their shitty anti-competitive behavior. it's a shame too because they could have had my money if they just weren't shitty about it.