Micron Abandons 3D XPoint Memory Technology
by Billy Tallis on March 16, 2021 6:00 PM ESTIn a sudden but perhaps not too surprising announcement, Micron has stated that they are ceasing all R&D of 3D XPoint memory technology. Intel and Micron co-developed 3D XPoint memory, revealed in 2015 as a non-volatile memory technology with higher performance and endurance than NAND flash memory.
Intel has been responsible for almost all of the commercial volume of 3D XPoint-based products, under their Optane brand for both NVMe SSDs and persistent memory modules in the DIMM form factor. Micron in 2016 announced their QuantX brand for 3D XPoint products, but never shipped anything under that brand. Their first and only real product based on 3D XPoint was the X100 high-end enterprise SSD which saw very limited release to close partners. Micron has now decided that further work to commercialize 3D XPoint memory isn't worth the investment.
Micron currently owns the only fab equipped to mass-produce 3D XPoint memory: the Lehi, Utah fab that was formerly the home of the Intel-Micron flash and 3D XPoint joint venture IMFT. Intel and Micron began splitting up their partnership in 2018, first parting ways for 3D NAND flash memory development, followed by dissolving the 3D XPoint partnership after completing development on the second generation 3D XPoint. In 2019, Micron exercised their rights to buy out Intel's share of the IMFT fab, leaving Micron as the sole owner of the fab and Intel in the position of buying 3D XPoint wafers from Micron to use in Optane products. Intel's Optane products have not been enough to fully utilize the capacity of that fab, and Micron's non-GAAP operating profits have been taking a hit of over $400 million per year in underutilization charges.
Micron is now putting that 3D XPoint fab up for sale, and is currently engaged in discussions with several potential buyers. Intel is the most obvious potential buyer, having recently begun the long process of selling their NAND flash and flash-based SSD business to SK hynix while keeping their Optane products. Intel has already moved their 3D XPoint R&D to Rio Rancho, NM but has not built up any 3D XPoint mass production capacity of their own; buying the Lehi, UT fab would save them the trouble of equipping eg. their NAND fab in Dalian, China to also manufacture 3D XPoint.
However, Intel is not guaranteed to be the buyer of the Lehi, UT fab. They've doubtless had opportunities to do so before as Intel and Micron unwound their partnership. Micron states that the Lehi, UT fab could be used to produce analog or logic ICs, not just memory—and that converting it to large-scale manufacturing of DRAM or NAND flash memory would not be as appealing to Micron as simply expanding capacity at their other existing fabs. With widespread semiconductor shortages affecting almost all corners of the industry, this fab is likely to sell quickly even if the buyer needs to put substantial effort into retooling.
Micron does not have a direct replacement lined up for 3D XPoint memory technology, but continues R&D into new memory and storage technologies. Micron's announcement is emphasizing a pivot toward developing memory products that will use the Compute Express Link (CXL) interface, which promises to be a vendor-neutral interface for DRAM and non-volatile memories such as 3D XPoint.
Related Reading:
Source: Micron
60 Comments
View All Comments
Kamen Rider Blade - Wednesday, March 17, 2021 - link
And it's thinking like that, that put Intel in trouble.3DXP should get it's own controller and the long term reliability of 3DXP should be a emphasis over the crappy P/E life cycle that modern TLC / QLC / PLC that the NAND industry is pushing.
Especially for your OS drive.
Dug - Thursday, March 18, 2021 - link
Why would you spend so much for OS drive? You load your OS once and done. There's not a lot of reading or writing done in any one workload. This type of technology is good for databases. You'll see servers load OS off a couple of slow drives including sd cards, because they just sit there. They don't need speed.MegaKraut - Tuesday, March 16, 2021 - link
An unfortunate impact of the prior Intel 3D Xpoint prioritization was to delay the Micron/Intel transition from planar to 3D NAND.Billy Tallis - Wednesday, March 17, 2021 - link
Really? IMFT were second to bring 3D NAND to market after Samsung, and Toshiba/SanDisk and Hynix were way behind IMFT. Intel even skipped the 16nm planar node in part because they were confident they could go straight from 20nm planar to 32L 3D. Whatever delay 3DXP may have caused for 3D NAND can't have been big.coschizza - Wednesday, March 17, 2021 - link
intel is leader in 3D NAND qldbrucethemoose - Wednesday, March 17, 2021 - link
Any non-volatile alternative to NAND or DRAM faces a huge uphill battle, due to how refined the tech is at this point.I don't think a breakthrough will happen until the scaling for either truly runs out of steam, which will light a fire under those paying for the R&D. And that's not too far away.
brucethemoose - Wednesday, March 17, 2021 - link
Also, I kinda saw this coming ever since XPoint's durability issues were published.Being expensive is one (potentially solvable) thing. But the durability issue throws a wrench in the fantasy of 3D XPoint replacing DRAM, and that's a problem that only seems to get worse with shrinks.
romrunning - Wednesday, March 17, 2021 - link
I do think Optane memory wasn't the right positioning for the tech. If Intel initially went all-in on Optane being the best thing in storage IO while continuing to research improving the top end (like 2nd gen), then it could slowly started to dominate the server storage market. I've been using SSDs in server storage for a while now, and it's amazing the benefits you get there. So they could have focused on getting the costs near premium NAND flash drive pricing as well as continuing to increase the top end, and Intel would have eventually dominated the enterprise direct storage market.But trying to also position it as a NVDIMM solution just wasn't the right time for it. Let the enterprise come to know, trust, and demand Optane first. Then jump into the NVDIMM side when you have your own costs lower on the mfg side, and have a bigger ready-made audience of storage users to sell into with your new type of memory.
t.s - Wednesday, March 17, 2021 - link
Well, they won't go that way, as it's the opposite of intel motto: 'milking everyone whenever you can'. So, not gonna happen.edzieba - Wednesday, March 17, 2021 - link
It never really made sense why Micron brought out Intel's stake in the 3DXP fab. Micron was an utter and complete failure at commercialising their tech, and seemed to be trying their hardest to bury it. Micron spent money on developing the tech, spent money on building the fab line, and then went on to spend even more buying out Intel's stake, while seemingly having difficulty selling a die themselves. Intel on the other hand were selling every die they could fab. It seems like an extremely good deal for Intel to sell their fab stake to Micron (with the wafer agreement guaranteeing supply), and then to be able to buy back that stake at a lower cost shortly after.It kind of mirrors the start of Chalcogenide PCM back in the 70s, when Intel collaborated with Energy Conversion Devices to build an Ovonic chip, which then got span off into Numonyx, which got brought up by Micron, and subsequently sat on.