Intel Optane Still not Dead, Orders Expanded by Another Quarter

[AleksandarK]

In July 2022, Intel announced that the company was winding down its Optane division, effectively discontinuing the development of 3D XPoint memory that it has been marketing for a long time. Once viewed as a competitive advantage, the support for Optane has been removed from future platforms. However, Intel has announced plans to extend Optane shipments by another quarter amidst additional stock or significant demand from customers buying Optane DIMMs for their enterprises. Initially set to ship the final Optane Persistent Memory 100-series DIMMs on September 30, Intel extends this date by three months to December 29, 2023.

Intel states, "Customers are recommended to secure additional Optane units at the specified 0.44% annualized failure rate (AFR) for safety stock. Intel will make commercially reasonable efforts to support last time order quantities for Intel Optane Persistent Memory 100 Series."



View at TechPowerUp Main Site | Source

 

[Daven]

I guess the warehouse workers found one last box of optane SSDs that didnt make it into the dumpster.

 

[dj-electric]

I guess the warehouse workers found one last box of optane SSDs that didnt make it into the dumpster.

I'm going to go ahead and claim that the association to optane cache, which is a completely different product btw, is a part of why Optane died.
No, this isn't Optane cache SSDs, read the article, slowly.

 

[Daven]

I'm going to go ahead and claim that the association to optane cache, which is a completely different product btw, is a part of why Optane died.
No, this isn't Optane cache SSDs, read the article, slowly.

Ok fine,

I guess the warehouse workers found one last box of optane CACHE that didnt make it into the dumpster.

Happy?

 

[ymdhis]

Are these compatible with Itanium servers?

 

[Daven]

Are these compatible with Itanium servers?

I think only Xeon Phi.

 

[bug]

I'm going to go ahead and claim that the association to optane cache, which is a completely different product btw, is a part of why Optane died.
No, this isn't Optane cache SSDs, read the article, slowly.

Neah, my money's on a roadblock they hit (either RnD or manufacturing). They couldn't improve it or drive down costs fast enough and it didn't make sense to keep it alive. Makes me sad, I still drool over Optane's 4k random read numbers

 

[Wirko]

Neah, my money's on a roadblock they hit (either RnD or manufacturing). They couldn't improve it or drive down costs fast enough and it didn't make sense to keep it alive.

That's what I think too - Intel and Micron never found a way to build tall stacks of those green and yellow bricks, so it was impossible to bring the cost down to near-NAND levels.
(And luckily, they also didn't find a way to compress many bits into one cell.)

 

[dgianstefani]

I'm still hoping it's just shelved.

Nothing, even now in gen 5 fairyland, comes close to optane real world performance or even a 10th of the cell longevity. People focus on its caching or RAM replacement aspects but again, those were pushed for their value argument. Pure optane storage, used as normal or scratch drives are where its at.

I swear, the "good enough" attitude combined with marketing's successful efforts to get buyers focusing on irrelevant numbers (see: sequential performance) will be the death of the human race eventually.

Some ark spaceship is gonna fail because the cockpit dashboard uses 64 GB EMMC or something. Like when $100k teslas died for that reason.

I really need to get around to buying one of the large optane AIC new while they're still around.

 

[bug]

I'm still hoping it's just shelved.

Nothing, even now in gen 5 fairyland, comes close to optane real world performance or even a 10th of the cell longevity. People focus on its caching or RAM replacement aspects but again, those were pushed for their value argument. Pure optane storage, used as normal or scratch drives are where its at.

I swear, the "good enough" attitude combined with marketing's successful efforts to get buyers focusing on irrelevant numbers (see: sequential performance) will be the death of the human race eventually.

Some ark spaceship is gonna fail because the cockpit dashboard uses 64 GB EMMC or something. Like when $100k teslas died for that reason.

I really need to get around to buying one of the large optane AIC new while they're still around.

Well, "good enough" is how natural selection works anyway. But stupidity (i.e. letting others decide what we should focus on) might just do the trick.

And yes, I'm 99% sure they don't just throw away the research, if some breakthrough presents itself, there may be another life for these. At the same time, Optane, take a number...

 

[Pizdarenkowitch]

Why bother with this obsolete POS if Race Track memory is not that far away???

Memory_on_the_racetrack.pdf

FOCUS | COMMENTARY. Memory on the racetrack Stuart Parkin and See-Hun Yang Racetrack memory stores digital data in the magnetic domain walls of nanowires. This technology promises to yield information storage devices with high reliability, performance and capacity. M. agnetic hard disk drives...

www.docdroid.net

 

[AnotherReader]

Why bother with this obsolete POS if Race Track memory is not that far away???

Memory_on_the_racetrack.pdf

FOCUS | COMMENTARY. Memory on the racetrack Stuart Parkin and See-Hun Yang Racetrack memory stores digital data in the magnetic domain walls of nanowires. This technology promises to yield information storage devices with high reliability, performance and capacity. M. agnetic hard disk drives...

www.docdroid.net

Racetrack memory has been in development since 2002. It doesn't look like it'll be available any time soon.

 

[Pizdarenkowitch]

Racetrack memory has been in development since 2002. It doesn't look like it'll be available any time soon.

I saw some latest videos on YT about this matter,and there they are talking to bring Race Track Memory 4.0 ... very soon.
Also,Super Ram wants to come too,take a look :

Adv Elect Materials - 2022 - Hodgson - ULTRARAM A Low‐Energy High‐Endurance Compound‐Semiconductor Memory on Silicon.pdf

Research Article www.advelectronicmat.de. ULTRARAM: A Low-Energy, High-Endurance, Compound-Semiconductor Memory on Silicon Peter D. Hodgson, Dominic Lane, Peter J. Carrington, Evangelia Delli, Richard Beanland, and Manus Hayne* memory seemingly necessitates a frail logic state that is easily...

www.docdroid.net

 

[thestryker6]

I'm still hoping it's just shelved.

Nothing, even now in gen 5 fairyland, comes close to optane real world performance or even a 10th of the cell longevity. People focus on its caching or RAM replacement aspects but again, those were pushed for their value argument. Pure optane storage, used as normal or scratch drives are where its at.

I swear, the "good enough" attitude combined with marketing's successful efforts to get buyers focusing on irrelevant numbers (see: sequential performance) will be the death of the human race eventually.

Some ark spaceship is gonna fail because the cockpit dashboard uses 64 GB EMMC or something. Like when $100k teslas died for that reason.

I really need to get around to buying one of the large optane AIC new while they're still around.

Honestly it seemed to me that the focus on expanding DRAM capacity is what doomed the product. Intel didn't seem to expect DDR4 capacity to skyrocket like it did which meant they weren't able to give more capacity just a slightly lower cost. The caching seemed to be a way to largely offset performance of HDDs which rapidly became obsolete in client computing due to NAND pricing tanking. They didn't integrate caching + NAND until a fair bit later (I want to say they only had 2 generations of these products).

The small Optane drives are fantastic for ZFS (I might have 6 of them in my server box), and probably if you use third party caching software to make tiers on Windows. The storage drives are absolutely fantastic and I'm still kicking around getting one of the first gen ones, but I don't have a current need and would prefer PCIe 4.0 but can't justify P5800X cost. It seems like they were stuck between a rock and a hard place pricing wise where they couldn't get it low enough for consumer without damaging enterprise sales. They also never seemed to advertise the storage aspect despite them being the best drives on the market.

I really hope it makes a return or something equivalent comes along because NAND is not the technology we should be relying on for storage.

 

[Frank_100]

Still waiting on HP and the memristors.

 

[Scrizz]

... NAND is not the technology we should be relying on for storage.

100% QFT

 

[unwind-protect]

Remind me which generations of Xeons supported these? I think from v5 on.

 

[thestryker6]

Remind me which generations of Xeons supported these? I think from v5 on.

Second Gen Scalable (Cascade Lake) so that would correspond to 10th Gen desktop.

 

[Pizdarenkowitch]

Emerging UK Start-Up Quinas Gets International Prize for its Disruptive Memory Innovations

Quinas Technology, which was originally spun-out of Lancaster University, has just gained a high-profile accolade for its ULTRARAM memory.

www.epdtonthenet.net

 

[Selaya]

There Is Nothing Wrong With Optane And 3D Xpoint (NASDAQ:INTC)

Both Intel and Micron have dropped their pursuit of 3D XPoint / Optane. There is nothing wrong with the well-received technology itself. Read more here.

seekingalpha.com