Comments Locked

34 Comments

Back to Article

  • gobaers - Thursday, October 18, 2018 - link

    RAMifications?
  • CaedenV - Friday, October 19, 2018 - link

    +1 This made my morning
  • prime2515103 - Saturday, October 20, 2018 - link

    The IMpact of this will be reMEMbered for years to come...

    Ok, that sucked never mind...
  • Impulses - Sunday, October 21, 2018 - link

    Way to drive it into the ground... Kids these days, that just don't understNand
  • ilt24 - Thursday, October 18, 2018 - link

    It would seem what is next is for Micron to continue with it's own 3D XPoint work in Lehi, while Intel does the same at it's factory in Albuquerque.
  • HStewart - Thursday, October 18, 2018 - link

    My guess is Intel has something better coming and desiring to get rid of fat in ram business.
  • sa666666 - Thursday, October 18, 2018 - link

    Total conjecture and guessing, but of course you would assume that all is right in Intel-land. Can't possibly be because they're doing poorly in other areas. They can't possibly be doing anything bad/wrong, correct?
  • Dragonstongue - Thursday, October 18, 2018 - link

    ^ 1000000000000% they have no choice but to trim costs before burn through reserves.
  • Dr. Swag - Friday, October 19, 2018 - link

    Right, I am sure they desperately need money since they have 10s of billions of dollars in cash and make over 10 billion a year!
  • philehidiot - Friday, October 19, 2018 - link

    Consider the shareholders. The CPU market is leaking away to a resurgent AMD and they must curb costs to maintain profit and therefore return to investors. No, they don't desperately need money but once their profits begin to drop, people will bug out and once that happens the share price will drop and so on and so forth. They MAY be trying to sell this off due to the risk entailed in order to sure up overall margins and therefore keep the balance sheets looking rosey. But this may also have been the long term plan knowing that Optane was generally niche anyway.
  • Eliadbu - Saturday, October 20, 2018 - link

    Intel for long time is not just CPU company
    And truth to be told their main focus today is not CPU at all, and it is a smart move since CPU improvement has reached a blockade you can't get much from IPC so you turn to small architectural optimization and the AMD METHOD of slapping more cores, Intel knowing that prefers to focus in fields like automotive, AI and GPUs for compute. Optane has a potential to access high market share in both storage and memory territory. Calling it niche is a shortsighted statement. NAND was in the same position that optane is today in the first generations. With time to come if the price would be able to come down enough it might push NAND aside and even might compete at the memory market.
  • Gondalf - Sunday, October 21, 2018 - link

    I don't see signs about what you are claiming.
    The real story is pretty simple: Intel has right now finished to double the capacity of Fab 68 and it is plenty of clean room to utilize for XPoint manufaturing. In China the costs are far lower than in USA so this is a good move to increase the operative profit.
  • HStewart - Friday, October 19, 2018 - link

    Total conjecture and guessing, but of course you would assume that all is wrong in Intel-land. Can't possibly be because they're doing something that would be good. They can't possibly be doing anything good, correct?
  • Bob-o - Thursday, October 18, 2018 - link

    Then you are not familiar with this situation. Intel had no choice in the matter. According to the agreement they signed years ago, Micron had the option of buying Intel out, the terms were completely spelled out. Micron has decided to exercise its option. That means they are bullish on their plans for 3D Xpoint, the price to buyout is dirt cheap. . . this is a positive for Micron, much less so for Intel.
  • wumpus - Friday, October 19, 2018 - link

    Interesting. Inexpensive memory is the last thing Intel wants. Obviously, Micron isn't necessarily keen on it themselves, but as long as they can rake in monopoly pricing on cheap to produce memory, all's well.

    The reason Intel hates cheap memory is that the cost of all the memory a server needs is so high it only justifies an expensive Intel processor (or possibly Epyc and on rare occasions an even more expensive IBM). With less expensive memory, ARM and AMD start to look far more attractive (although I wouldn't ignore the cases where AMD competes regardless of the cost of DRAM).

    Yes, I just want 64GB for the price of 16GB (and ideally a HBM2 cache of DRAM). Maybe 2020.
  • Eliadbu - Saturday, October 20, 2018 - link

    What your comment makes no sense. You don't buy processors by high expensive your memory is. you buy them by your budget and needs. And on contrary the more expensive ram is the organization would buy either cheaper processor or less CPUs to keep the cost down which is bad for sale in both cases. And the "HBM2 cache" is nonsense. if you knew how HBM2 works.
  • Kamgusta - Friday, October 19, 2018 - link

    You people have no idea how big companies work.
    The goal of the Micron/Intel joint-venture was to create 3D layers and ReRAM technologies.
    They succeed.
    They did such a great job they will work 12 more months in refining (second-generation products).
    The joint-venture can be closed as it reached its goal.
    Both Micron and Intel have the rights and fabs/equipments to create products based on these new standards - they did and they will do.
    Today, Micron decided to buy the IMTF personal and equipment for 1,5B$ as Intel do not need them.
    Micron and Intel are still friends, so they decided to not compete in the same market: Micron will take the automotive and mobile, Intel will take the high-end computing.
    Is Optane a commercial flop? Maybe. Intel knew it as dind't expect more revenues than 10% of its NAND business.
    Are the 3D layers and the resistive random access memory technologies a flop? Ehm... no.
    By 10 years we'll use only products based on these tecnologies.
    End of story.
  • Eliadbu - Saturday, October 20, 2018 - link

    Remember it is just first gen what we have right now. Back when NAND was first gen it didn't fare well either vs HDD in sales. So you can't call it flop yet (and the brand name optane is not going anywhere soon) .
  • Lord of the Bored - Friday, October 19, 2018 - link

    In other words, Intel's entire Optane business was a complete fiasco and they have made grave mistakes over the past few years?
    Or in short... "Optane? More like Hypetane!"
  • PeachNCream - Friday, October 19, 2018 - link

    Sure, sure, something better is coming from Intel like the shining light of the Sun as it falls gracefully upon a blooming meadow after breaking through the dispersing rain clouds. Only the purity of Intel working alone, not tainted by the filth of a partner corporation like Micron, could offer such a wonderful future to we mere huddled masses. Like you, HStewart, I am eager to cavort to the highest hilltop from which I shall cast my song of praise into the wind for all to hear once the wise marketing gurus see fit to lift their silken sheets of non-disclosure.
  • HStewart - Friday, October 19, 2018 - link

    Actually Intel has new technology for solid state storage - 32 Terabytes on stick for servers

    https://newsroom.intel.com/news/worlds-densest-tot...

    Intel® 3D NAND technology
  • SunLord - Friday, October 19, 2018 - link

    Outside of being the first to have 32Tb via QLC in a NF1/Ruler format it's not exactly anything special outside of the new server friendly format
  • FullmetalTitan - Friday, October 19, 2018 - link

    What a bad read. Intel has been hemorrhaging talent and research has stalled across many products, but surely this partnership ending is all roses for Intel.
  • Byte - Friday, October 19, 2018 - link

    With the stalling of 3D Xpoint, i think they might just use it as the buffer in DRAMless SSDs. We are seeing tons of them, and performance can suffer quite a bit. We are seeing rubbish Laptops with 4GB Ram and 16GB Optane, so I can see this as a possibility. I cannot believe a vast majority of computers still come with HDD in physical stores.
  • Eliadbu - Saturday, October 20, 2018 - link

    Simply it is price most people need more than 128gb or 256 gb drive and for 512gb or 1tb ssd drive laptop you would be paying much more than what many people can afford so a mechanical disk is the optoion for more competing budget machines.
  • melgross - Thursday, October 18, 2018 - link

    This article was written very strangely. It’s stiff and leaves out words in a number of sentences.
  • AshlayW - Friday, October 19, 2018 - link

    It read fine to me?
  • abufrejoval - Friday, October 19, 2018 - link

    My impression was that Intel had planned NV-RAM to become a) extremely attractive in terms of price/capacity b) an Intel monopoly to fight off p-Series, AMD and ARM.

    Phase change failed to deliver the magic, so far, and seems ever less likely to deliver it going forward. Instead it is becomming a commodity that is hard to sell while it was adding a significant technical liability to server and BIOSes for a functionality that never came.

    So the first thing we'll probably see go now is those NV-DIMM sockets.
  • BurntMyBacon - Friday, October 19, 2018 - link

    @Anton Shilov: "This can be one reason why the two decided to dissolve the partnership and focus on individual goals both for volatile (NAND) and non-volatile (post-3D XPoint) types of memory."

    Perhaps I'm missing something, but I thought NAND was non-volatile. Seems like a requirement for storage through power cycles.
  • name99 - Friday, October 19, 2018 - link

    Yeah, I think the distinction Anton was TRYING to make was between (large) BLOCK-addressed storage (like NAND, or HD) and BYTE-addressed storage (more realistically, cache-line addressed storage) like 3D-XPoint was supposed to be (but never actually shipped).

    Point is, cache-line addressed storage can (at least in principle, modulo a whole bunch of changes that need to be made in the CPU and OS) be used as DRAM, either to boost the effective amount of DRAM, or to provide persistent DRAM. You can get to it "directly" without going through a block layer, and that reduction in latency and no need for thinking in large blocks allows for a whole lot of new possibilities, even if the storage is a few x slower than "real" DRAM.
  • edzieba - Friday, October 19, 2018 - link

    Looks like Micron can never resist squandering Chalcogenides whenever given the opportunity. If they can't sell their 3D XPoint dies (while Intel has no issue whatsoever shifting their entire output), then nobody can!
  • skis4hire - Friday, October 19, 2018 - link

    Intel is going to continue development of 3D XPoint at their fab in New Mexico:
    https://www.abqjournal.com/1219130/intel-moves-som...
  • alacard - Friday, October 19, 2018 - link

    "This can be one reason why the two decided to dissolve the partnership and focus on individual goals both for volatile (NAND) and non-volatile (post-3D XPoint) types of memory."

    WTF!!! are you saying here?
  • Santoval - Saturday, October 20, 2018 - link

    "This can be one reason why the two decided to dissolve the partnership and focus on individual goals both for volatile (NAND) and non-volatile (post-3D XPoint) types of memory."
    I believe you meant "non-volatile NAND and volatile post-3D XPoint" here. Unless you meant "volatile DRAM/HBM and non-volatile post-3D XPoint."

Log in

Don't have an account? Sign up now