Micron will finish out their obligations to Intel under their current wafer supply agreement, which commits them to producing 3D XPoint for at least several more quarters. But this definitely puts more pressure on Intel to secure a long-term manufacturing plan for 3DXP, because Micron plans to cut off 3DXP production as soon as they're allowed.
remember: IBM went into the PC business intentionally without making the guts of the machine, but buying in those guts. in true IBM fashion, they picked the most needy, and compliant, vendor around. thus Intel and the 8088. if Mitch (or anyone else) hadn't made 1-2-3 in 8088 assembler, neither M$ nor Intel would be the companies they became. it's better to be lucky than dumb.
It would be surprising if Intel went away completely anytime soon, even if they continue to fumble, but they are at serious risk of losing their position as the top chipmaker for desktops, laptops, workstations, and servers.
For now, they still have the brand recognition and vendor partnerships to remain the leader volume-wise, but that's definitely subject to change in the coming couple years if they can't get their act together again. Maybe the door is even finally opening for non-x86.
This is funny. His name is Japanese. Roughly, "Baka" is idiot and "Toroi" is a fermented broth dish. If you're still looking, why'd you chose this name? It's silly.
Someone who didn't like my ideas at the New York Times or Washington Post (comments section) — can't remember which — labelled me 'Oxford's janitor', which I thought was indeed droll trolling. I like the name, actually. A janitor is, after all, someone whose job it is to take out the trash.
what exactly do we gain from that? amd is slowly taking intel's place if you look at the situation right now and if the situation continues amd will become the new intel in terms of prices and practices. so we need intel as we needed amd 3 years ago.
We have ARM now. Plus RISC-V. Different arch, yes, but with the most popular OS (Android) can be installed on multiple different arch, I dont think it's a problem for majority of people that only use computer for teleconference, messaging, read news, etc..
Too bad HP's memristor with SK Hynix never became a working product!
This phase change stuff never seemed to have nearly as much potential.
Can't help thinking about all these NV-DIMM-only sockets on all these motherboards now approaching replacement: They never had a chance of being filled!
There are a lot of technological advancements that come with R&D on products like this, regardless of whether a product ever ships. Larrabee also comes to mind as a similar example of a failed retail push with some incidental R&D benefits for other projects.
I knew this was never going to take off. It was highly expensive and low in capacity. 3dxpoint seems even worse now because there are pcie4 based ssd's now which have high throughput. The only market for these are specific server workloads. There's nowhere near even of those server workloads to make this financially viable. It is only a matter of time until intel gives up on it too. I'm sure china would like to buy it though.
I agree. PCI 4.0 was the nail in the coffin at least for Desktop usage. The upcoming Direct-Storage API makes it terminal. Funny thing is I still own the Star Citizen ship that was included in the 900P Optane drive.
Direct Storage api (gpudirect) only reduces overhead by eliminating the requirement of goiny through the os's block layer but not the problem of media access latency times. It's the latter one xpoint is attempting to address.
I think that Micron just gave up too quickly. 3d Xpoint is where NAND was 10 years ago expensive and limited capacity but like NAND then it has advantages over other technologies. It's disadvantage is NAND is good enough for most uses so it's not compelling to go the expensive route. Micron wants to invest its money and resources somewhere else and it is understandable, the question is how further does Intel is willing to push the technology.
While it's true that there are Gen4 (and upcoming Gen4) NAND based SSDs which have incredible transfer rates, for something like 4K Q1T1 random read/write, NAND is still much, MUCH slower than Optane.
A high end current SSD like the SN850 or 980 Pro may deliver 60-70MB/s under such conditions, while Optane will deliver ~300MB/s. The same goes for queue latency (extremely low) and IOPS (extremely high, across all queue depths).
That we're not going to see a successor to the 905P at the enthusiast desktop level is genuinely sad. For a lot of workloads, the jump from an SSD to Optane is just as significant as the jump from HDD to SSD was.
I hope they, or someone else, revisit it outside of the datacenter.
Yes, Optane was easily the best thing to have for a boot/system drive, and the technical benefits at lower queue depths (which is the typical I/O load on desktops) were great.
But neither Intel nor Micron (especially Micron) put more effort into lowering the costs. I'd easily buy an Optane drive over a premium SSD if it was 50-100% higher cost, but they couldn't even get it down into that range.
Very sad for storage as the industry keeps going down, instead of up, the performance ladder with QLC, PLC, etc.
I suspect the differentiation is more in memory DIMMs rather than storage SSD. Direct access let's you have vast pools of (albeit slow) system memory. Effectively this lets you combine the worlds of "big data" and "in memory" compute.
"Effectively this lets you combine the worlds of "big data" and "in memory" compute."
makes one wonder whether Oracle TimesTen and SAP HANA might run at least OK with a true NVM and not have to worry about power and writing to storage and such. cutting out more than just some of the OS routines...
They're excellent as OS drives and cache drives. But SLC is pretty good for that too, especially for more read-oriented workloads. And pseudo-SLC caching doesn't require a new SSD controller, and is a lot more flexible than having to decide how many dies of 3DXP vs dies of 3D NAND to include.
If Intel had done their own NVMe SSD controller that could interface to both 3D NAND and 3DXP and allowed them to implement caching in the SSD rather than be limited by the hassle of custom storage drivers for motherboards and Windows, then products like the Optane Memory H10/H20 could have been a lot more interesting. But Intel doesn't think it's worth their effort to design their own consumer-focused SSD controller.
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.
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.
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.
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.
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.
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.
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.
"while seemingly having difficulty selling a die themselves" They didn't even try to make more than one product to sell. The X100 was the only product.
Yeah, Micron really had the worst marketing for 3DXP. They didn't even want to seed X100 products among reviewers, it seemed.
So when you have virtually no push yourself to get your product into the enterprise (or even consumer side) and you also have basically one major customer, then yeah, you're not going to make more money with it. Pretty bad business planning & execution on Micron's part.
Why would you even need 3DX Point or Optane, when you have the lowest quality garbage like QLC and PLC and whatever LC is coming soon to the consumer market with tons of bs variations with controllers, DRAM, SLC level caching and what not.
The R&D is high but the rewards would benefit everyone, they do not want that since they want easy cash and cheap ways to get billions which is where NAND is at along with the <infinite>LC SSDs flooding the market now even Chinese are going to flood the market.
'Why would you even need 3DX Point or Optane, when you have the lowest quality garbage like QLC and PLC and whatever LC is coming soon to the consumer market with tons of bs variations with controllers, DRAM, SLC level caching and what not.'
It is absolutely worth losing 90% endurance, increasing latency by 3000%, and increasing power usage by 250% to get 10% more density!
Nooo.. the most promising technology that was not just on paper (or an idea) has been (half) scrapped. What a pity. I would have really liked a 3D XPoint SSD at a decent price.
NAND is just becoming worse and worse each generation.. it won't be much longer that it will have to be replaced before extra silicon needed to try to correct (and most probably guess) the right content of the wearing cells will be bigger (and more power consuming) than the section containing those memory cells.
Hope that Intel will believe in it and will continue develop it to decrease its costs and improve quality.
Not gonna happen. Intel pricing their 3D XPoint at half DRAM price. And knowing intel, they rather euthanize the product rather than changing their plan.
Too bad. When Micron bought Intel's share I thought XPoint will become widely available. Intel actually killed it making some of XPoint based products Intel bound. I'd buy a 500GB M.2 drive even if it were more expensive than NAND.
Really strange. The reason I don't buy Optane is that it is too expensive. Yet they are not making as much of it as they could. Doesn't it seem like a price vs. demand problem? Lower price = more demand. But clearly Micron isn't expecting an increase in orders from Intel or they wouldn't put it up for sale.
It’s always possible that it’s just too difficult to produce, and so can’t be brought down significantly in cost. If that’s true, I can understand Micron’s decision. Intel might feel differently, but then the question is why advances haven’t come regularly, as they do with DRAM and NAND?
I’ve seen a lot of new technologies that were supposed to change everything die, because they couldn’t be produced at the prices they needed to be at. This could be one of those. Theoretically feasible, but not feasible financially, or even technologically.
Microns repeated mention of CXL as an alternative to 3DXP is... odd, to say the least. It would be like Seagate announcing they are abandoning HAMR in favour of PCIe-based drives: the storage hardware itself and the interface that talks to it are two different things. There is nothing whatsoever stopping Micron creating CXL-connected devices that use 3DXP other than Micron themselves.
Yeah, it's a bit of a non sequitur at first glance. But I think the underlying admission is that 3DXP and any similar persistent memory cannot be successful at scale without a pre-existing ecosystem around an interface like CXL. Relying on Intel to add 3DXP support directly to their CPUs and letting them have a monopoly on Optane DCPMM prevented 3DXP from being commoditized in the way it needed to be to be successful. I expect Micron doesn't want to try again with a different memory technology unless it has a clear path to a large TAM.
Disappointing. I very much want to see Instant Computing. We should've gotten there by 2000 or so, but instead PCs and phones are inexplicably slow. Everything but video encoding should be instant, every app should be open and ready in 100 ms or so. Booting should be a second or two tops. Anything happening in an app should also be at no more than 100 ms latency.
Optane would've been good for Instant Computing, though we probably shouldn't need it. The latency of an SSD over PCIe 3.0 or 4.0 should enable those 100 ms latencies easy. There must be an enormous number of CPU cycles spinning just to do simple things like opening an app, things that were actually faster in the 1980s. Microsoft and Intel could do very well with a new generation of OSes and architectures, but they have no vision.
Exactly. I do not understand why Microsoft doesn't care about user experience. The latest version of Office takes about 5 seconds to open up Word, and there's often lag in right-click menus and other pop-ups. Yet Office 2002 is lightning fast. It seems software devs care more about packing in features while not giving a crap about responsiveness.
"Yet Office 2002 is lightning fast. It seems software devs care more about packing in features while not giving a crap about responsiveness."
way back when (when? no longer recall), Gates answered complaints about Windows (again, which version?) performance with... "let the hardware fix it". that's less and less likely these days.
The amount of time I spend each day waiting for files to open probably adds up to minutes. That's on quite modern 2018 hardware (i5, SSD). Xpoint/Optane wouldn't make it any better, either, as you can see from benchmarks that measure real-world performance.
"I very much want to see Instant Computing. We should've gotten there by 2000 or so, but instead PCs and phones are inexplicably slow. Everything but video encoding should be instant, every app should be open and ready in 100 ms or so. Booting should be a second or two tops"
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
60 Comments
Back to Article
Jorgp2 - Tuesday, March 16, 2021 - link
Damn, wonder if Optane will become even more scarceBilly Tallis - Tuesday, March 16, 2021 - link
Micron will finish out their obligations to Intel under their current wafer supply agreement, which commits them to producing 3D XPoint for at least several more quarters. But this definitely puts more pressure on Intel to secure a long-term manufacturing plan for 3DXP, because Micron plans to cut off 3DXP production as soon as they're allowed.baka_toroi - Tuesday, March 16, 2021 - link
IT'S OVER INTEL IS FINISHED!Eliadbu - Tuesday, March 16, 2021 - link
I can't count how many times I have heard it before but this pesky Intel is still here.baka_toroi - Tuesday, March 16, 2021 - link
Wintel existed before and it has served them for quite some time. Those times are over.FunBunny2 - Wednesday, March 17, 2021 - link
remember: IBM went into the PC business intentionally without making the guts of the machine, but buying in those guts. in true IBM fashion, they picked the most needy, and compliant, vendor around. thus Intel and the 8088. if Mitch (or anyone else) hadn't made 1-2-3 in 8088 assembler, neither M$ nor Intel would be the companies they became. it's better to be lucky than dumb.twtech - Monday, March 22, 2021 - link
It would be surprising if Intel went away completely anytime soon, even if they continue to fumble, but they are at serious risk of losing their position as the top chipmaker for desktops, laptops, workstations, and servers.For now, they still have the brand recognition and vendor partnerships to remain the leader volume-wise, but that's definitely subject to change in the coming couple years if they can't get their act together again. Maybe the door is even finally opening for non-x86.
ballsystemlord - Tuesday, March 16, 2021 - link
This is funny. His name is Japanese. Roughly, "Baka" is idiot and "Toroi" is a fermented broth dish.If you're still looking, why'd you chose this name? It's silly.
baka_toroi - Tuesday, March 16, 2021 - link
Wonder if Unicode will work here.Toroi - とろい
(adj-i) slow (slightly pejorative); dull; stupid
It's silly, that's why I chose it back in 2004. Kinda regret it tbh. Not gonna create a new account.
ballsystemlord - Tuesday, March 16, 2021 - link
That's ok. I'm not criticizing your choice. It's just very unusual.Oxford Guy - Wednesday, March 17, 2021 - link
Baka is always good for humor value. It's good to keep one's sense of humor, even into old age.Oxford Guy - Wednesday, March 17, 2021 - link
Someone who didn't like my ideas at the New York Times or Washington Post (comments section) — can't remember which — labelled me 'Oxford's janitor', which I thought was indeed droll trolling. I like the name, actually. A janitor is, after all, someone whose job it is to take out the trash.mindless1 - Wednesday, March 17, 2021 - link
Thanks for staying on-topic!yeeeeman - Wednesday, March 17, 2021 - link
what exactly do we gain from that? amd is slowly taking intel's place if you look at the situation right now and if the situation continues amd will become the new intel in terms of prices and practices. so we need intel as we needed amd 3 years ago.baka_toroi - Wednesday, March 17, 2021 - link
Never meant to imply it's a good thing.Anyway, x86 isn't the monopolistic hog it used to be. The market is very different now.
t.s - Wednesday, March 17, 2021 - link
We have ARM now. Plus RISC-V. Different arch, yes, but with the most popular OS (Android) can be installed on multiple different arch, I dont think it's a problem for majority of people that only use computer for teleconference, messaging, read news, etc..Samus - Monday, March 22, 2021 - link
If Yahoo is still in business, Intel is far from finished :Pabufrejoval - Tuesday, March 16, 2021 - link
Too bad HP's memristor with SK Hynix never became a working product!This phase change stuff never seemed to have nearly as much potential.
Can't help thinking about all these NV-DIMM-only sockets on all these motherboards now approaching replacement: They never had a chance of being filled!
MikeMurphy - Tuesday, March 16, 2021 - link
There are a lot of technological advancements that come with R&D on products like this, regardless of whether a product ever ships. Larrabee also comes to mind as a similar example of a failed retail push with some incidental R&D benefits for other projects.spaceship9876 - Tuesday, March 16, 2021 - link
I knew this was never going to take off. It was highly expensive and low in capacity. 3dxpoint seems even worse now because there are pcie4 based ssd's now which have high throughput. The only market for these are specific server workloads. There's nowhere near even of those server workloads to make this financially viable. It is only a matter of time until intel gives up on it too. I'm sure china would like to buy it though.Chaser - Tuesday, March 16, 2021 - link
I agree. PCI 4.0 was the nail in the coffin at least for Desktop usage. The upcoming Direct-Storage API makes it terminal. Funny thing is I still own the Star Citizen ship that was included in the 900P Optane drive.tuxRoller - Wednesday, March 17, 2021 - link
Direct Storage api (gpudirect) only reduces overhead by eliminating the requirement of goiny through the os's block layer but not the problem of media access latency times.It's the latter one xpoint is attempting to address.
Eliadbu - Wednesday, March 17, 2021 - link
I think that Micron just gave up too quickly. 3d Xpoint is where NAND was 10 years ago expensive and limited capacity but like NAND then it has advantages over other technologies. It's disadvantage is NAND is good enough for most uses so it's not compelling to go the expensive route. Micron wants to invest its money and resources somewhere else and it is understandable, the question is how further does Intel is willing to push the technology.Slash3 - Wednesday, March 17, 2021 - link
While it's true that there are Gen4 (and upcoming Gen4) NAND based SSDs which have incredible transfer rates, for something like 4K Q1T1 random read/write, NAND is still much, MUCH slower than Optane.A high end current SSD like the SN850 or 980 Pro may deliver 60-70MB/s under such conditions, while Optane will deliver ~300MB/s. The same goes for queue latency (extremely low) and IOPS (extremely high, across all queue depths).
That we're not going to see a successor to the 905P at the enthusiast desktop level is genuinely sad. For a lot of workloads, the jump from an SSD to Optane is just as significant as the jump from HDD to SSD was.
I hope they, or someone else, revisit it outside of the datacenter.
romrunning - Wednesday, March 17, 2021 - link
Yes, Optane was easily the best thing to have for a boot/system drive, and the technical benefits at lower queue depths (which is the typical I/O load on desktops) were great.But neither Intel nor Micron (especially Micron) put more effort into lowering the costs. I'd easily buy an Optane drive over a premium SSD if it was 50-100% higher cost, but they couldn't even get it down into that range.
Very sad for storage as the industry keeps going down, instead of up, the performance ladder with QLC, PLC, etc.
Jon Tseng - Wednesday, March 17, 2021 - link
I suspect the differentiation is more in memory DIMMs rather than storage SSD. Direct access let's you have vast pools of (albeit slow) system memory. Effectively this lets you combine the worlds of "big data" and "in memory" compute.FunBunny2 - Wednesday, March 17, 2021 - link
"Effectively this lets you combine the worlds of "big data" and "in memory" compute."makes one wonder whether Oracle TimesTen and SAP HANA might run at least OK with a true NVM and not have to worry about power and writing to storage and such. cutting out more than just some of the OS routines...
Lolimaster - Wednesday, March 17, 2021 - link
It's not about brute speed but endurance and a near order of magnitude less latency.Kamen Rider Blade - Tuesday, March 16, 2021 - link
I really wish they would try to make these take off as basic OS drives.They have the right latency factor and latency once the drive is filled to function as ultra low latency OS drives.
Billy Tallis - Tuesday, March 16, 2021 - link
They're excellent as OS drives and cache drives. But SLC is pretty good for that too, especially for more read-oriented workloads. And pseudo-SLC caching doesn't require a new SSD controller, and is a lot more flexible than having to decide how many dies of 3DXP vs dies of 3D NAND to include.If Intel had done their own NVMe SSD controller that could interface to both 3D NAND and 3DXP and allowed them to implement caching in the SSD rather than be limited by the hassle of custom storage drivers for motherboards and Windows, then products like the Optane Memory H10/H20 could have been a lot more interesting. But Intel doesn't think it's worth their effort to design their own consumer-focused SSD controller.
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.
Adramtech - Wednesday, March 17, 2021 - link
"while seemingly having difficulty selling a die themselves" They didn't even try to make more than one product to sell. The X100 was the only product.romrunning - Wednesday, March 17, 2021 - link
Yeah, Micron really had the worst marketing for 3DXP. They didn't even want to seed X100 products among reviewers, it seemed.So when you have virtually no push yourself to get your product into the enterprise (or even consumer side) and you also have basically one major customer, then yeah, you're not going to make more money with it. Pretty bad business planning & execution on Micron's part.
Silver5urfer - Wednesday, March 17, 2021 - link
Why would you even need 3DX Point or Optane, when you have the lowest quality garbage like QLC and PLC and whatever LC is coming soon to the consumer market with tons of bs variations with controllers, DRAM, SLC level caching and what not.The R&D is high but the rewards would benefit everyone, they do not want that since they want easy cash and cheap ways to get billions which is where NAND is at along with the <infinite>LC SSDs flooding the market now even Chinese are going to flood the market.
Oxford Guy - Thursday, March 18, 2021 - link
'Why would you even need 3DX Point or Optane, when you have the lowest quality garbage like QLC and PLC and whatever LC is coming soon to the consumer market with tons of bs variations with controllers, DRAM, SLC level caching and what not.'It is absolutely worth losing 90% endurance, increasing latency by 3000%, and increasing power usage by 250% to get 10% more density!
Lolimaster - Wednesday, March 17, 2021 - link
And I was hoping new SSDs with xpoint as a non volatile extra cache after ram where with the option allocate most frequent used data.shabby - Wednesday, March 17, 2021 - link
Hope there's a fire saleCiccioB - Wednesday, March 17, 2021 - link
Hope not, or many will just get burned...CiccioB - Wednesday, March 17, 2021 - link
Nooo.. the most promising technology that was not just on paper (or an idea) has been (half) scrapped.What a pity. I would have really liked a 3D XPoint SSD at a decent price.
NAND is just becoming worse and worse each generation.. it won't be much longer that it will have to be replaced before extra silicon needed to try to correct (and most probably guess) the right content of the wearing cells will be bigger (and more power consuming) than the section containing those memory cells.
Hope that Intel will believe in it and will continue develop it to decrease its costs and improve quality.
t.s - Wednesday, March 17, 2021 - link
Not gonna happen. Intel pricing their 3D XPoint at half DRAM price. And knowing intel, they rather euthanize the product rather than changing their plan.tommo1982 - Wednesday, March 17, 2021 - link
Too bad. When Micron bought Intel's share I thought XPoint will become widely available. Intel actually killed it making some of XPoint based products Intel bound. I'd buy a 500GB M.2 drive even if it were more expensive than NAND.gdansk - Thursday, March 18, 2021 - link
Really strange. The reason I don't buy Optane is that it is too expensive. Yet they are not making as much of it as they could. Doesn't it seem like a price vs. demand problem? Lower price = more demand. But clearly Micron isn't expecting an increase in orders from Intel or they wouldn't put it up for sale.melgross - Thursday, March 18, 2021 - link
It’s always possible that it’s just too difficult to produce, and so can’t be brought down significantly in cost. If that’s true, I can understand Micron’s decision. Intel might feel differently, but then the question is why advances haven’t come regularly, as they do with DRAM and NAND?I’ve seen a lot of new technologies that were supposed to change everything die, because they couldn’t be produced at the prices they needed to be at. This could be one of those. Theoretically feasible, but not feasible financially, or even technologically.
edzieba - Friday, March 19, 2021 - link
Microns repeated mention of CXL as an alternative to 3DXP is... odd, to say the least. It would be like Seagate announcing they are abandoning HAMR in favour of PCIe-based drives: the storage hardware itself and the interface that talks to it are two different things. There is nothing whatsoever stopping Micron creating CXL-connected devices that use 3DXP other than Micron themselves.Billy Tallis - Saturday, March 20, 2021 - link
Yeah, it's a bit of a non sequitur at first glance. But I think the underlying admission is that 3DXP and any similar persistent memory cannot be successful at scale without a pre-existing ecosystem around an interface like CXL. Relying on Intel to add 3DXP support directly to their CPUs and letting them have a monopoly on Optane DCPMM prevented 3DXP from being commoditized in the way it needed to be to be successful. I expect Micron doesn't want to try again with a different memory technology unless it has a clear path to a large TAM.JoeDuarte - Saturday, March 20, 2021 - link
Disappointing. I very much want to see Instant Computing. We should've gotten there by 2000 or so, but instead PCs and phones are inexplicably slow. Everything but video encoding should be instant, every app should be open and ready in 100 ms or so. Booting should be a second or two tops. Anything happening in an app should also be at no more than 100 ms latency.Optane would've been good for Instant Computing, though we probably shouldn't need it. The latency of an SSD over PCIe 3.0 or 4.0 should enable those 100 ms latencies easy. There must be an enormous number of CPU cycles spinning just to do simple things like opening an app, things that were actually faster in the 1980s. Microsoft and Intel could do very well with a new generation of OSes and architectures, but they have no vision.
AnnonymousCoward - Monday, March 22, 2021 - link
Exactly. I do not understand why Microsoft doesn't care about user experience. The latest version of Office takes about 5 seconds to open up Word, and there's often lag in right-click menus and other pop-ups. Yet Office 2002 is lightning fast. It seems software devs care more about packing in features while not giving a crap about responsiveness.FunBunny2 - Friday, March 26, 2021 - link
"Yet Office 2002 is lightning fast. It seems software devs care more about packing in features while not giving a crap about responsiveness."way back when (when? no longer recall), Gates answered complaints about Windows (again, which version?) performance with... "let the hardware fix it". that's less and less likely these days.
AnnonymousCoward - Friday, March 26, 2021 - link
The amount of time I spend each day waiting for files to open probably adds up to minutes. That's on quite modern 2018 hardware (i5, SSD). Xpoint/Optane wouldn't make it any better, either, as you can see from benchmarks that measure real-world performance.peevee - Friday, April 2, 2021 - link
"I very much want to see Instant Computing. We should've gotten there by 2000 or so, but instead PCs and phones are inexplicably slow. Everything but video encoding should be instant, every app should be open and ready in 100 ms or so. Booting should be a second or two tops"Hear hear!
peevee - Friday, April 2, 2021 - link
MBA mismanagement strikes again.