Intel Offers More Insight On Its 3D Memory (itworld.com)

itwbennett writes: When Intel and Micron Technology first announced the 3D XPoint memory in July, they promised about 1,000 times the performance of NAND flash, 1,000 times the endurance of NAND flash, and about 10 times the density of DRAM. At OpenWorld last week, Intel CEO Brian Krzanich disclosed a little more information on the new memory, which Intel will sell under the Optane brand, and did a demo on a pair of matching servers running two Oracle benchmarks. One server had Intel's P3700 NAND PCI Express SSD, which is no slouch of a drive. It can perform up to 250,000 IOPS per second. The other was a prototype Optane SSD. The Optane SSD outperformed the P3700 by 4.4 times in IOPS with 6.4 times less latency.

Comments

So which is it?

[fnj]

1,000 times the performance, or 6 times the performance? Somebody needs to get the story right with the hyperbole.

Re:So which is it?

[Anonymous Coward]

... and about 10 times the density of DRAM.

How is this possible? 1 bit DRAM is a single transistor.

Re:So which is it?

[Anonymous Coward]

Both? You do realize there is more than one performance metric?

Re:So which is it?

[pushing-robot]

They claimed the technology had the potential to hit 1000 times faster than current flash memory... they didn't specify when or what flash they were comparing to.

In any case, this is an early prototype spanking the top of the line current technology. That's impressive in my book.

Re:So which is it?

[suutar]

I think they're figuring "a package with a gigabit can take one tenth of the space of a gigabit of dram, because stacking"

Re:So which is it?

[Anonymous Coward]

They probably mean areal density.
So to answer your question, probably by stacking layers upon layers of the stuff.

Re:So which is it?

[The-Ixian]

It kind of reminds me of the old "jet stream oven" infomercials.

"It is microwave fast ... 2x faster than cooking it in a conventional oven"

Re:So which is it?

[Anonymous Coward]

They said about 4.4x the perf of the flash in that demo. So ~1.1 million iops per sec? If that is true it may actually be faster than RAM.

We shall see. Tech demo and all...

Re:So which is it?

[Anonymous Coward]

The memory might be faster, it always seems to be the interface that slows things down.

Re:So which is it?

[Anonymous Coward]

Any single component being 1000 times faster will not make the entire system that much faster.

It will however eliminate the bottleneck that it posed to the entire system up to the point that another part of that system becomes the bottleneck

Having any one component produce a 600% increase in performance is phenomenal

Re:So which is it?

[unixisc]

How many times the cost, and the price?

Re:So which is it?

[dafradu]

And no industry will deliver a product 1000x times faster/better overnight, not as long a competitor can't do the same. They will sell you a thing 2 or 3 times faster every few years, maximizing profit.

Re:So which is it?

[Anonymous Coward]

Amdahl has a lower UID than you do.

Re:So which is it?

[Anonymous Coward]

I wonder if we should standardize on RPM of the items in question. Everyone knows a 10,000 RPM SSD is faster than a 7200 RPM SSD.

Re:So which is it?

[nojayuk]

There's a whole raft of other things to consider before this tech changes the IT world -- how much does it cost, how many separate fabs can produce it so there's no single-point-of-failure that could constrain supply, how much redesign of existing chipsets is required to integrate it into current server/workstation/mobile phone designs, what's the failure rate in service, power dissipation and cooling requirements etc.

Saying that the demo suggests it can be implemented into existing platforms with little difficulty. Of course as Napoleon once said, "There are lies, damned lies and rigged demos." Time will tell.

Re:So which is it?

[Anonymous Coward]

definitely 1,000 times the performance (assuming hypothetical perfect interconnects and the planets are properly aligned)

Re:So which is it?

[ShanghaiBill]

How is this possible? 1 bit DRAM is a single transistor.

No. A DRAM bit is a single transistor plus a capacitor. The capacitor has to be recharged every few milliseconds, which is what makes it "dynamic".

Re:So which is it?

[Kjella]

Well you can deliver a car with 1000x the performance in horsepower, but it won't go 1000x faster. Since they've been intentionally vague about exactly what metric they based that claim on, it could be anything really. Beating a top of the line enterprise NVMe drive several times over is impressive at any rate. I look forward to seeing actual product.

Re:So which is it?

[funwithBSD]

Even if it is truly 1000x faster, the rest of the architecture is not designed to make full use of it.
No way any any of the current bus technologies could handle even a 10X improvement to its full extent.

Re:So which is it?

[swb]

If this technology can be adapted to fit into SAS-compatible packaging at MLC/3D NAND pricing this will rock the enterprise storage world for sure.

Entire brands/products in enterprise storage are built around features like caching/tiering that charge you $30k for a little flash and way more than they should for spinning rust under the promise that they'll deliver flash performance for all your workloads, most of the time.

Doing so requires beefy controllers to run elaborate tiering schemes, and along with the sky-high prices for media makes them extremely expensive and extremely profitable.

If (and this is a big if) you can get SLC durability at MLC pricing and simultaneously cut the controller cost (need less compute because you're not bothering with tiering, far less software complexity), suddenly you could have someone selling entry level 24 drive shelves with millions of IOPS and sustained transfers that will melt SAS-12 cables.

Basically it will make sense to quit using rust at all without paying nosebleed pricing at pretty much any scale.

Re:So which is it?

[fyngyrz]

You're clearly trying to spin this to match your narrative. Well, I'm here to tell you it's a spindly argument; you can't just serve stuff like that up on a platter, step by step, and expect everyone to nod their heads. Are you tracking me solidly now? Or are you still in a state?

Re:So which is it?

[nojayuk]

If this tech makes it into the marketplace at reasonable prices it's not going to be hanging off SAS-12 cables or any other serial links at that rate, it will be more tightly integrated with the CPU bus to deliver on the R/W and access speed improvements. Even PCI is a possible bottleneck if this 3D flash can deliver what Intel are claiming for it. Comparing its performance to DRAM is a "tell" and shows what they're thinking; this may be the fabled "non-volatile RAM" solution that's been the Holy Grail researchers have been trying to develop pretty much ever since RAM was invented. (Yes, I know there are battery-backed-up RAM solutions that claim to be non-volatile but they're only non-volatile until the battery power runs out).

Re:So which is it?

[DRJlaw]

You're clearly trying to spin this to match your narrative. Well, I'm here to tell you it's a spindly argument; you can't just serve stuff like that up on a platter, step by step, and expect everyone to nod their heads. Are you tracking me solidly now? Or are you still in a state?

Don't be dense. We're not quite as susceptible to your magnetic personality as you believe. Now step off and voice your opinions somewhere else.

Re:So which is it?

[Coren22]

DRAM is a type of RAM.

Re:So which is it?

[Anonymous Coward]

Both.
Two different performance numbers: latency and speed, sort of like how horsepower and miles-to-the-gallon are different performance numbers.

Re:So which is it?

[goarilla]

For that to succeed you need more than 2 manufacturers (Intel & Micron) though.

Re:So which is it?

[Anonymous Coward]

RPM is just a fancy way to write Hz, which again is another way to express time. In the case of drives it is of interest to indicate a maximum access time.
10,000 RPM is equivalent to 6 ms and 7200 RPM is closer to 8,3 ms.
Clearly the marketing team should state that the SSD is equivalent to 2,400,000 RPM.

Re:So which is it?

[MobileTatsu-NJG]

They claimed the technology had the potential to hit 1000 times faster than current flash memory... they didn't specify when or what flash they were comparing to.

Just to be up-front this is a topic I'm very ignorant about, it was only casual curiosity that made me peek into the comment section. But does't Intel normally announce a new design with where the intend for it to land long before they announce their products that are only blips along their roadmap? For example: "With this our new Pentanium Matrix we'll reach 64 cores and 10 gigahertz."... and a few months later: "Now announcing our Titticaca processor with 16 cores at 3.09ghz"

Eh I dunno, but now you have an idea of why I don't pay a lot of attention to these announcements until I'm reading them on Newegg.

Re:So which is it?

[Anonymous Coward]

It is always a hen and egg situation.
Removing the drive from the equation will make any speedup in other parts more meaningful.

Re:So which is it?

[hey!]

I note that they refer to a 1000x improvement in "performance", and a 6.4x improvement in "latency". Latency is one time-related performance metric; throughput might be the other be alluded to.

Imagine two water hoses. One is ten feet long and one inch wide; the other is inches in diameter and a hundred feet long. Which can deliver water "faster"? Well, when you turn the spigot on water comes out of the ten foot first; but if you're filling up a swimming pool the hundred foot long hose is faster.

Re:So which is it?

[Anonymous Coward]

Early research that I've read indicates they're selling it in a RAM form-factor first, and then later looking to do things such as PCI-style drives in the coming years.

Re:So which is it?

[Anonymous Coward]

Hmmm, the new CPU RAM memory disguised as the old feromagnetic Core memory of days gone by. On the other hand the transistors just might use ferromagnetics already.

Re:So which is it?

[PRMan]

Don't Samsung and HP already have competing technologies?

Re:So which is it?

[swb]

If it's cheap enough, it'd still be useful as a hard disk replacement even if it's not the most optimal way to deploy it. Fixed storage isn't going away tomorrow even if this turns out to be the holy grail of NVRAM.

I'm not sure it is, either, as its durability is compared to SSDs, not to DRAM.

Even if it was a game changer, it'd be years before hardware and upstream architectures adapted to more optimal uses for it. And if it doesn't have DRAM durability, it's more likely to be used as permanent storage anyway. Conventional flash is packaged in just about every interface, from PCIe to USB2, even though its more useful in some versus others.

Re:So which is it?

[Michael Woodhams]

This is a quibble, but non-volatile RAM has only been the Holy Grail since about 1970. Prior to that, magnetic core memory was the standard RAM technology and is non-volatile. (To quibble the quibble, for a short period of time Williams tubes were the state-of-the-art (indeed, only) RAM, and they are volatile. Alan Turing played with Williams tubes.)

Re:So which is it?

[r0kk3rz]

Comparing its performance to DRAM is a "tell" and shows what they're thinking; this may be the fabled "non-volatile RAM" solution that's been the Holy Grail researchers have been trying to develop pretty much ever since RAM was invented. (Yes, I know there are battery-backed-up RAM solutions that claim to be non-volatile but they're only non-volatile until the battery power runs out).

From TFA

The company will also come out with Optane DIMMs later this year for early testers, which will combine the performance of DRAM with the capacity and cost of flash. That means a two-socket server with Optane DIMMS will have a total of 6 TB of addressable memory, "virtually eliminating paging between memory and storage, taking performance truly to a whole new level.

Seems like we're going to find out soon, 6TB of addressable non-volatile ram sounds like a game changer

Re:So which is it?

[nojayuk]

Seems like we're going to find out soon, 6TB of addressable non-volatile ram sounds like a game changer

A server system really needs to be able to address hundreds or thousands of terabytes of storage, not just six. That's what I meant by the server system designers having to revamp the basic concepts of a computer with RAM separate from secondary storage (HDDs or SSDs on a separate bus) to one with a "flat" storage architecture. The OS will have to change too to take account of the blurring or total elimination of the difference between addressable RAM space and secondary storage, and getting that to work reliably and efficiently will take some time and involve some serious mistakes too, I expect. Sharing storage over a network will also be a challenge, as will backup processes.

Re:So which is it?

[Anonymous Coward]

It will also revolutionize OS design, "file" concept etc when the differtiation between RAM memory and disk space is gone. Where is my save button?

Re:So which is it?

[goarilla]

I don't think so. They will in a few years time and in the mean time they'll market tuned versions of their high end SSD's as being comparable.
But I'm someone who believes they will deliver on some of their hype.

Re:So which is it?

[mr_mischief]

This is getting to be a heady argument. Why don't you two park it over there and find some way to re-float this issue? You're both coiled and it's creating a giant resistance.

Re:So which is it?

[mr_mischief]

It really depends on what type of server we're talking about. Is it a front-end web server? Is it a middleware application server? Is it a database server for small to medium databases? Is it a big DB cluster? Is it a media or document storage system? Is it a hypervisor on a hardware node offering shards of its resources to VMs? These have different storage and processing needs.

In the short term, there are a few solutions for the OS and applications. Many applications will keep as much in memory as possible already. Most OSes support RAM disks, so you could put a very fast virtual disk into your main RAM if you have 4 or 6 TiB of RAM and an application absolutely needs to think it's writing to disk. Also, I doubt segmented storage is going away entirely. You'll still have disks, SSDs, or separate blocks of this stuff available for truly cold storage if you need it. You just won't use them very much compared to today.

Re:So which is it?

[KingMotley]

Early demos indicate they are thinking of doing PCIe-style drives, probably first. Which makes sense since it'll be a drop in replacement that nearly anyone can use immediately rather than as a new type of RAM that would require some pretty large architecture changes.

Re:So which is it?

[KingMotley]

A server system really needs to be able to address hundreds or thousands of terabytes of storage, not just six.

Only in very niche markets is that true. Most servers don't need anything near 6TB of storage, let alone 6TB of (D)RAM.

Re:So which is it?

[KingMotley]

You could do that, but probably not for the forseeable future. Files will still be needed, and a standardized way of accessing them will still be needed. Most software will likely use the same old APIs to access them, seek, etc but the driver will be seriously simple. In theory you could remove them, but then what would you do about CDs? DVDs? Backup Tapes and drives? Network connections? Network drives? Your OS will still need a unified way of accessing all that stuff, so it just makes sense to just extend what we have than throw it all away and start new... in most cases. You just call the memory-mapped I/O API, but now it just returns a pointer to where the data actually resides and the actually memory-mapping is silly simple when you need to wring every last bit of speed out of something.

Re:So which is it?

[KingMotley]

Neither, cause I only have a 5/8" spigot, so neither will hook up to it and I'll drag out my old hose from the garage.

Re:So which is it?

[nojayuk]

Most servers don't need anything near 6TB of storage, let alone 6TB of (D)RAM.

Many servers do need access to that sort of storage (and a hundred times more) and it would help if those servers run the same OS on similar hardware as other servers with less demand do. The alternative is for the sort of species differentiation that hobbles High Performance Computing (HPC) because there are few standards and a lot of hand-written system code flying in close formation, different on each machine.

I expect, if anything comes of this 3D flash RAM that there will be a flurry of Good Intentions by assorted BigCorps and LittleStartups which will evolve into two or three usable hardware and OS implementations that everyone coalesces around and then we move forward from there. The intervening period will be fun to observe, from a safe distance at least.

Oh, and are you claiming that 6TB should be enough RAM for anyone? There's a Slashdot meme for that...

Re:So which is it?

[KingMotley]

Most servers that need to access that amount of storage don't do so locally, they are doing so through things like SANs because maintaining that number of high speed low capacity drives isn't trivial and best consolidated across servers. Getting a 6TB pool would require at least 10 600GB 15k drives (the largest capacity 15k RPM drive that seagate currently makes), and that's not going into your 1x server blade, and typically isn't a great solution.

Network and remote access drives like SANs aren't going away, but that isn't your typical server. For each one of those, there is a ton of servers that have less than 6TB of storage.

And no, I never claimed 6TB of RAM would be enough for everyone, but it's enough for a very very high percentage of people today. But you are correct in that there will likely always been a need for a secondary type of storage interface. USB drives, backups, network storage, cloud storage devices, etc.

Re:So which is it?

[fnj]

Darn good discussion, all.

Re:So which is it?

[swb]

I agree wholeheartedly that the SAN storage consolidation model isn't going away. It's logical and it's been so widely adopted with so many dollars and man-hours invested in it that it might never go away, regardless of storage device changes.

That being said, the "hyperconverged" software defined model of server nodes possessing some storage and clustering it into virtual SANs is gaining some traction. VMware has vSAN and Windows 2016 server will extend storage spaces to allow for this.

The challenge for this model has always been storage scaling requires node scaling and even if you can cut out the SAN, it remains an exercise in cost modeling to see if increased node licenses plus node costs (now that they're fatter with local storage) results in meaningful cost savings. Plus, there are questions of performance and operational complexity versus a traditional SAN model,

All that being said, if Optane offers "DIMM" modules and you can pack 6 or 12 TB easily on a motherboard at MLC NAND pricing, I can see where this model might gain a lot of traction. Relatively cheap and simple nodes with extremely fast and large scale internal storage on 10+ Gb ethernet could make it an interesting alternative.

Bla bla bla

[sunderland56]

Yeah, we *really* believe Intel's marketing statements; I mean, they've been 100% accurate in the past.

Look, just shut up and start shipping product. The IT community will come up with their own performance figures.

Re:Bla bla bla

[Anonymous Coward]

Yeah, we *really* believe Intel's marketing statements; I mean, they've been 100% accurate in the past.

Look, just shut up and start shipping product. The IT community will come up with their own performance figures.

I think you mean 1000 percent accurate!

Re:Bla bla bla

[pr0nbot]

eah, we *really* believe Intel's marketing statements; I mean, they've been 100% accurate in the past.

Yeah - at the time they even had the nerve to claim they'd be 600% accurate.

Re:Bla bla bla

[Anonymous Coward]

Look, just shut up and start shipping product.

If they want to milk the cow, the IT community at large will not get their dirty hands on these reasonably prized hard-drive replacements until the competing technologies are already in the market. Years, I tell you, years!

I'm guessing both.

[DumbSwede]

Increasing Memory Speeds 1000x will not lead to a straight 1000x increase in operations. There are undoubtedly other bottles necks in processing. What for instance is the theoretical max throughput of the memory interface used (is it a modified SSD interface)? What CPU overhead is involved? Don't expect your computer to perform 1000x better across the board just because one component is 1000x faster.

Re:I'm guessing both.

[Anonymous Coward]

This is a common issue with all of these things.

Even if you improve just one component to some super futuristic new hardware, it will still be horribly limited by everything else it connects to.
Your super-fast internet means nothing when you are still connected to the phone grid using aluminum phone lines.

Everything limits everything. Something that needs to be taken in to serious consideration when designing new hardware, figuring out ways around it and maybe even contributing to projects for new future standards that are higher bandwidth/speed/whatever.

Re:I'm guessing both.

[Anonymous Coward]

is it a modified SSD interface?

No. It'll show up using a modified DDR4 interface or an NVMe interface. You'd have to look at tech news sites (not Slashdot) to find that info.

Re:I'm guessing both.

[Anonymous Coward]

According to Intel, they plan on using the DDR4 interface and I believe NVMe for some of the Optane devices.

Of course, on a intel chipset.

6.4 Times Less Latency

[sexconker]

"6.4 times less latency" means that if the latency of the baseline thing you are comparing against is X, then the latency of the new thing has a latency of 6.4 times X less than X, which is X minus 6.4 times X, which is negative 5.4 X.

The latency we're discussing is a measurement of time (and up until Intel's amazing breakthrough it was always positive).
This means that Intel has discovered tachyons, invented a time machine, and violated causality in general. Either that, or "journalists" and marketers don't know what they're doing.

Re:6.4 Times Less Latency

[PhrostyMcByte]

Came here for this. Tech writers should not be able to get away with using nonsense metrics.

Re:6.4 Times Less Latency

[Anonymous Coward]

I assume they mean that something like (new latency) = (old latency) / 6.4. Of course that's not a vindication of the writers for using sloppy language but one must assume the 6.4 number means *something* or they would have made up a way bigger number.

Re:6.4 Times Less Latency

[harrkev]

I think they mean that the old way takes 6.4 times as long as their newest toy.

Re:6.4 Times Less Latency

[Anonymous Coward]

Then why didn't they say that instead of the impossible and stupid mumbo-jumbo they said instead?

Re:6.4 Times Less Latency

[KingMotley]

It has 6400 less millitimes as fast!

XPoint smells like an arch inflection point...

[davyCrockett]

Would expect my circa 2017 laptop purchase to have 1 TB of XPoint memory, dynamically used as RAM and 'SSD' (32G and 'nearly' 1TB), deliver a 5 to 10x increase in general performance, and cost relatively the same... Reasonably stupid idea?

Re:XPoint smells like an arch inflection point...

[Anonymous Coward]

Only the "cost relatively the same" bit.

Re:XPoint smells like an arch inflection point...

[Anonymous Coward]

Performance gain will not be that significant for most applications. It will be similar to the improvement seen going from spinning hard drive to flash hard drive. The most dramatic performance benefit will be instant suspend/resume.

Re:XPoint smells like an arch inflection point...

[CrashNBrn]

I figure it should be less than $5000 for the 3D-drive. (1,000GB/16GB * $75 == $4688). Although it is Intel, it might require your first born.

Re:XPoint smells like an arch inflection point...

[KingMotley]

No, but you can expect your 2017/2018 laptop to have a general performance increase of maybe 10-15%, but loading things and searching for files will be 150%-500% faster depending on application, and suspend/resume may be silly fast.

It doesn't matter

[Anonymous Coward]

Programmers still write code that unnecessarily thrashes the CPU cache like hell. No matter how fast you make it, idiots will access it in a pattern that completely wipes out any performance gains.

Fix stupidity (and laziness) first.

Re:It doesn't matter

[Pseudonymous Powers]

Fix stupidity (and laziness) first.

Yeah, that's a realistic and practical precondition for any project.

Re:It doesn't matter

[gnupun]

Maybe CPU, OS and compiler tools should offer feedback to the programmer on how the program is affecting various levels of cache first, then the programmer will improve. Start with the laziness of the hardware/software vendors.

Re:It doesn't matter

[godrik]

They do. It is called Performance counters. Check V-Tune and PAPI.

RAM size will decrease

[Overzeetop]

I mentioned this in a story a few days ago, but this brings it back to the forefront. The fastest SSDs have sequential write speeds about an order of magnitude slower than typical DDR3/DDR4 SDRAM. Increasing SSD speeds to be on par with DDR means you may actually need far less RAM than you did in the past because swap operations have very little cost. If endurance ticks up three orders of magnitude (as claimed), you might start considering dropping DRAM entirely for low end computers, perhaps with an increase in CPU cache sizes to reduce misses.

Now that seems ridiculous, but so did having video processing on the CPU a decade ago. And yet the Iris and Iris Pro that Intel is putting on the Skylake chips are on par with lower end dedicated video cards that can run even current AAA games at reasonable resolutions and framerates.

Re:RAM size will decrease

[Anonymous Coward]

perhaps with an increase in CPU cache sizes to reduce misses.

This is not going to work, because your typical code is written by 3rd-worlder outsourcée interns who know jackshit about not thrashing the cache.

Re:RAM size will decrease

[KingMotley]

DRAM would just become a 4th-level external CPU cache.

RAM Drive?

[ed1park]

How does performance compare to the fastest RAM drive? And what would be the estimated cost per IOPS of each? (RAM vs SSD vs Optane)

The best is yet to come...

[TomGreenhaw]

Using XPoint as a successor to mass storage in my mind is short term thinking. Maybe its a quick way to sell the technology in the near term, but certainly not the best use case.

We should get away from mass storage altogether and use this as replacement for RAM. It will take a rethinking of operating system structure, but promises to provide instant on computers with all programs and data always loaded and ready for immediate access. Database systems would immediately be orders of magnitude faster because all data is always ready for access.

I for one will not miss virtual memory...

Re:The best is yet to come...

[Tapewolf]

We should get away from mass storage altogether and use this as replacement for RAM.

It doesn't have enough write endurance to do that. You could burn the stuff out with a FOR loop.

Re:The best is yet to come...

[Anonymous Coward]

Where is my save button? where is my fopen() ? This mifht completely change concept of "file" and file based security as we know it...

Re:The best is yet to come...

[TomGreenhaw]

Damn, good point.

I guess we're back to VM until endurance can be addressed.

Re:The best is yet to come...

[Big Hairy Ian]

Yes but when the Virtual Memory is on Optane it's going to have a shitload less impact. Also your idea could still have legs just allocate the static areas of your program to Optane and the dynamic to regular ram.

Re:The best is yet to come...

[TomGreenhaw]

I got to thinking about this problem.The L1,2 and 3 cache on the CPU would largely mitigate this. The trend has been to increase the size of the on die CPU cache. Perhaps a vastly increased L3 cache in the gigabytes and a wear levelling non volatile ram controller would fully address this problem.

Hardware is rate limiting

[duckintheface]

This comparison says nothing at all about 3DXP except that it is much faster than NAND. With NAND, it is the NAND memory itself that limits the speed. With 3DXP memory, it is the PCIe connection hardware that is the slowest component and therefore rate limiting for the entire retrieval speed.

When Intel/Micron says that the 3DXP is 1000 times faster than NAND, they mean that it has only 1/1000th of the latency. You will never see that speed in an SSD drive. The speed of 3DXP will only be realized as a DIMM module in a custom designed server with all the software modifications optimized for it. 3DXP is revolutionary for in-memory applications running in server farms. And once Intel includes 3DXP on the die with the processor, nothing currently envisioned will be able to compete with it.

BTW, although Intel will have a great advantage using this technology, from what I can tell it was actually Micron that invented (or developed from an early purchased prototype) this memory. I'm still waiting for Micron to start telling us what materials were used and how this memory actually works. That will tell us what its ultimate limits are.

Re:Hardware is rate limiting

[KGIII]

Wouldn't these be fast enough to use as RAM? Sure, maybe not for VRAM on a gaming rig or something but, say, for a server chugging away managing databases?

Re:Hardware is rate limiting

[nhat11]

From reading this and Intel's constant announcement that this tech will be faster then RAM and there won't be any difference between RAM and HDD

Re:Hardware is rate limiting

[duckintheface]

Well, 3DXP is random access so in a sense it is already RAM. It will be about 1/10th as fast as current RAM but it will be cheaper and more dense and non-volatile. So in some applications (in-memory apps in cloud servers) 3DXP may replace current RAM. An all-3DXP system might be faster than a combination of current RAM with SSD memory.

Re:Hardware is rate limiting

[KGIII]

Thanks for explaining. I can see this as having some very valuable use cases. Imagine, to go with my earlier thought - if you will, being able to pretty much page a database that's nearing a TB in size. My background is in working with heavy data sets (traffic modeling) that there are infinite data points that one could enter. Close enough to infinite that the word is close to valid. (It's similar to attempting to model chaos.) Now, in the late 1990s, we were nearing the point where we'd be working with as much as a TB of data - in the 1990s. Lots and lots and lots of disks all throughout a number of clustered servers including multiple storage arrays.

Now, we'd sometimes run models that would take a couple of weeks to complete (and this only got more complex when we began to model pedestrian traffic as well as vehicular traffic). Now, we were pulling data from spinning platters and and I imagine we were working with not much more than 16 GB per server - maybe even a quarter of that. It would have been revolutionary to be able to page an entire database like that. Then again, there have already been so many revolutions over the years.

Again, thanks for explaining. I figured I'd explain what I'd been thinking and where I would expect to see some use and asking questions is a good way for me to learn things.

Re:Hardware is rate limiting

[KGIII]

As I mentioned in a separate reply. This may not seem important to some people but where I still the owner of my business, I'd be damned excited at the potential. Imagine, if you will, being able to page a huge data set for the purpose of deterministic modeling. I'd expect exponential speed increases from the days of spinning platters. Of course, there's much more RAM available already and I've been out of the industry for eight years... Still, it seems extremely likely to have some good results on lower-end things like clusters. They still do clustering, right?

*sighs* I do kind of miss keeping up with all of this stuff.

Re:Hardware is rate limiting

[Tough Love]

Well, 3DXP is random access so in a sense it is already RAM. It will be about 1/10th as fast as current RAM but it will be cheaper and more dense and non-volatile. So in some applications (in-memory apps in cloud servers) 3DXP may replace current RAM. An all-3DXP system might be faster than a combination of current RAM with SSD memory.

Write latency is the big point that Intel glosses over in these PR releases. Given that they only claim 6.4 times "latency" improvement I expect the bulk of that is write latency, measured in tens of microseconds. If that is anywhere close to the truth then it means that xpoint is definitely not RAM-like, and you won't suddenly be expecting it to save the entire state of your OS on power off because the OS would slow to glacial speeds due to orders of magnitude higher write latency.

MarketerSpeak

[Anonymous Coward]

Its kind of like when dubious hard drive ads tout a 6Gb/s transfer speed when it has a SATA III interface. Never mind that the drive itself is incapable of moving data faster than 120MB/s no matter how fast the interface is. Personally, I'm looking forward to commercial products based on this new technology, but I would be foolish to think that it is going to be 1000x faster overall than my SSD and 1000x smaller (or 1000x bigger capacity) than my DRAM. If it is just 2x or 3x as fast; is not volatile; and doesn't cost an arm and a leg, then I will be excited.

RAS syndrome

[Lord Duran]

250,000 IOPS per second, right up there with your LCD display, PDF format, and PIN number.

Re:RAS syndrome

[Gondola]

One I've been seeing more lately that you can add to that list is "LED light."

Its The pcie interface people

[avandesande]

Yes, it is only six times faster- it has probably saturated the PCIe interface. Intel has already said as such that this would be an issue and that a new interface will be needed to accommodate the rams capabilities.

Under-Hype?

[siphonophore]

Am I the only one who thinks this technology is shockingly under-hyped? It eliminates a 50-year old performance anchor, neutralizes the biggest challenge in Computer Science, and makes a supercomputer out of an SoC.

It came out of nowhere, but I believe Intel's claims. They wouldn't restart memory manufacturing in their own facilities if the tech wasn't ready for prime time.

Re:Under-Hype?

[real-modo]

No, I don't think so.
At one write per second per memory cell, a device with 1000 times the endurance of NAND would last ... about a hundred days. RAM cells get updated on the order of milliseconds rather than seconds.

This tech won't reduce the need for RAM. It's a better NAND, not a replacement for RAM. It may allow reduction in the quantity of RAM required where performance is not critical. It's very welcome, but no miracle cure for our computing ills.

It may also enable a renaissance in Harvard-architecture machines, which split program storage from data storage. Programs tend not to change as much as data does. (Firefox, Chrome, and Fedora excepted, of course).

Re:Under-Hype?

[twokay]

Luckily it speak for its self. No need for the engineers to even speak to the marketing department. They just need to demo it.

Re:Under-Hype?

[siphonophore]

I see that endurance spec now. DRAM appears to be safe until they can address that.

I was imagining this would create a chip w/ 1 TB of L3. I guess that's a breakthrough or two away yet.

Re:Under-Hype?

[Tough Love]

This tech won't reduce the need for RAM. It's a better NAND, not a replacement for RAM.

If it performs anywhere new hype levels then it is indeed a replacement for the RAM that would otherwise be used to cache flash or disk. For a lot of use cases, that means most of the RAM in the box.

Re: Coren22's desperation, lies, & libel

[Anonymous Coward]

So I take it you and this other dude won't be having breakfast together tomorrow?

Coren22 proven a TROLL (NSA/GCHQ?)

[Anonymous Coward]

See subject - OR didn't you say:

"Maybe I should change my signature again just to rile him up some more." - by Coren22 (1625475) on Tuesday November 03, 2015 @10:07AM (#50855451) FROM http://slashdot.org/comments.p...

behind my back (I can't see sigs) & KGIII noted it:

"In an earlier thread, I saw that APK quoted your signature" - by KGIII (973947) on Monday November 02, 2015 @10:22PM (#50852845) FROM http://slashdot.org/comments.p...

Which I SHUT DOWN due to your lies about me on AD + DNS (GPO too from my security guides I see you've read, that are geared to single stand alone machines NOT networked ones but I advise vs. using external DNS with AD there too, here) -> http://slashdot.org/comments.p...

---

* You're a disgusting LIAR & burying yourself!

---

DEFENSE INDUSTRY? Coren22 from http://slashdot.org/comments.p...

"Theory" here - you working for the NSA/GCHQ now?

They tend to "recruit from within"!

They're KNOWN to attack SECURITY software (like mine) https://theintercept.com/2015/...

(If so THEY PICKED BADLY using YOU as a lapdog - (not theory ->) you're brain-damaged w/ Aspergers as you admit- "the sins of the father" = visited on his kids too)

Dumb - folks like me help SECURE folks via wares like mine - folks in NSA/GCHQ are spying on us is NOT helping folks in the US!

This "theory" of mine wouldn't surprise me 1 bit - considering GCHQ hacked /. https://www.techdirt.com/artic...

Not after proof I put up (IF you're their crony tell your "handlers" they're busting on the WRONG guy for "character assasination" - I help do the RIGHT thing, not the wrong one spying on US folks! I protect 'em)

Wouldn't be a 1st: I've had PROFESSIONAL trolls try it (Cito) & advertisers' cronies (AndyMadigan & RayMorris) do it on /. - I dusted + busted 'em.

APK

P.S.=> You've bring it on yourself (signatures? Punk! I've shown you're technically inept & I doubt you're MCSE, SystemEngineer, & Security - my posts show otherwise)... apk

Coren22 proven a LYING punk

[Anonymous Coward]

"APK doesn't think that DNS servers are worth running and seems to believe that somehow Microsoft Active Directory can run without DNS." - by Coren22 (1625475) on Tuesday October 27, 2015 @12:58PM (#50811615)

Where'd I say AD will run minus DNS Coren22? I've said AD = internal network DNS dependent as far back as 2007 http://forums.tweaktown.com/wi...

(Searching this in BOLD "To warn users who have ActiveDirectory/AD LAN-WAN setups to NOT use external DNS servers!" referring to OpenDNS suggestions for those using AD stupid in the POSTS BEFORE IT in my security guides for users (geared to stand alone single machines no less), & right there on that page proves it stupid - so even if you posted as myself someplace here on /. "impersonating me", I have your ass NOW, shithead!)

I've also stated MANY TIMES I use remote DNS in OpenDNS @ home (but not @ work on AD networks + exchange/outlook: Free OpenDNS model doesn't work with AD dependent Exchange + Outlook specifically you lying little imbecile).

I also don't hardcode in "every site there is under the sun" is why, so I have to use DNS, but OpenDNS & rarely.

I also RARELY MISS A LOOKUP since I put where I spend a good 95++% of my time online in my favorite sites into hosts @ the TOP of hosts for utmost LOCAL FASTER RESOLUTION SPEEDS and more reliability vs. Open DNS (not OpenDNS) resolvers being abused, Kaminsky redirect poisoned DNS servers (of which 99.999% of ISP DNS are not proofed against to this very day even though a patch exists which OpenDNS uses), rogue DNS servers, and yes ROUTERS with bushwhacked by malware DNS settings (happening a LOT lately).

Hardcodes in hosts are faster than remote DNS, waste less resources than local dns in power, cpu cycles, RAM, & other I/O by FAR considering ALL THE PARTS of such a setup in programs, data, I/O, & power (especially if setup as a separate machine).

APK

P.S.=> You're a disgusting liar... apk

Coren22's desperation, lies, & libel

[Anonymous Coward]

"I guess we should avoid your crap, it looks like it is marked as malware. Good luck getting that removed." - by Coren22 (1625475) on Monday November 02, 2015 @03:52PM (#50850445)

False positive: I've wrote 'em long ago, no response vs. 60++ REPUTABLE sources (not nobodies) below that fries you Coren22!

Is that your fake site for more lies Coren22?

Lying about me LIKE YOU DID HERE punk -> http://slashdot.org/comments.p... ??

---

MalwareBytes' hpHosts Admin (MalwareBytes employee) hosts & recommends it -> http://hosts-file.net/?s=Downl... & MalwareBytes = BEST antivirus per this VERY recent testing of them all http://www.av-test.org/en/news...

&

It's safe proven by 57 antivirus programs recently in BOTH its 64-bit model https://www.virustotal.com/en/...

+

Its 32-bit model too https://www.virustotal.com/en/...

More "SALT IN YOUR WOUNDS" -> http://f.virscan.org/APKHostsF...

APK

P.S.=> /.'ers say my work is good too:

"his hosts program is actually pretty good" - by xenotransplant (4179011) on Monday August 10, 2015 @03:34PM (#50287195)

"I like your host file system." - by Karmashock (2415832) on Wednesday September 09, 2015 @03:57PM (#50489401)

"APK is kinda right... I've given up on JS based adblocking and gone to blackholing in /etc/hosts, just like it was back in the 90s. The computational load has gotten intolerable for any ad-blocking using JS. I've tried his hosts file generating software. It works." - by bmo (77928) on Thursday October 15, 2015 @11:30AM (#50736071)

"his hosts tool is actually useful for those cases in which one does indeed want to locally block stuff outright while consuming minimum system resources" by alexgieg (948359) on Friday September 25, 2015 @09:57AM (#50596461)

It will be bigger than Bubble Memory

[Anonymous Coward]

This reminded me of the fiasco technology Bubble Memory.

Re:It will be bigger than Bubble Memory

[Tough Love]

This reminded me of the fiasco technology Bubble Memory.

You remind me of somebody who can't read numbers.

Re: Coren22's desperation, lies, & libel

[Anonymous Coward]

FFS give it a fucking rest already APK. Really, just stop.