Slashdot Mirror
Researchers Make RAM From a Phase Change We Don't Entirely Understand (arstechnica.com)
An anonymous reader quotes a report from Ars Technica: We seem to be on the cusp of a revolution in storage. Various technologies have been demonstrated that have speed approaching that of current RAM chips but can hold on to the memory when the power shuts off -- all without the long-term degradation that flash experiences. Some of these, like phase-change memory and Intel's Optane, have even made it to market. But, so far at least, issues with price and capacity have kept them from widespread adoption. But that hasn't discouraged researchers from continuing to look for the next greatest thing. In this week's edition, a joint NIST-Purdue University team has used a material that can form atomically thin sheets to make a new form of resistance-based memory. This material can be written in nanoseconds and hold on to that memory without power. The memory appears to work via a fundamentally different mechanism from previous resistance-RAM technologies, but there's a small hitch: we're not actually sure how it works. The two mechanisms used to change the resistance have been reported in the journal Nature Materials.
So they switched substrates from unobtanium to unexplanium?
-Unresolved symbol? Byte me!
we're not actually sure how it works.
Call it ERAM aka Emo RAM because "YOU DON'T UNDERSTAND ME AT ALL!" ;)
Anons need not reply. Questions end with a question mark.
What's the worst thing that could possibly happen?
--something witty
I'm glad Purdue is getting some dividends out of that nanotechnology center they built 10 years ago. That thing always gave me the creeps. Probably because I watched too much Star Trek as a kid.
One of our competitors trademarked the term "hypothesis". From now on, we will call them "boneheaded ideas".
Perhaps especially in the field of medicine and pharmaceuticals, there are plenty of products that we see working, but nobody knows exactly how.
Wikipedia has an entire category for just that:
https://en.wikipedia.org/wiki/...
"Nerds store their data on punched paper tape, made of paper, which we don't entirely understand."
Go ahead and tell me everything you know about trees.
That form of matter has a name - toilet paper.
For example the brain works...
Would've been nice if you'd given an example.
Politics; n. : A religion whereby man is god.
Generally, we don't care about RAM holding its state beyond a power cycle
This is because our systems are designed with the assumption that RAM is volatile.
If RAM held its value, there would be no need to have a distinction between RAM and "Disk". Computers would boot far faster. Databases would be right on the memory bus, with no need to "sync" to reliable storage. Many, many applications and services could be faster, simpler and more reliable.
honestly, flash degradation hasn't been an issue in RAM modules, since, forever. In flash storage, the degradation hasn't been shown to be much of an issue with MLC let alone SLC drives.
Flash degradation is not a problem because Flash is only used in applications where the degradation won't be a problem. If a Flash replacement can be faster and have unlimited write cycles, then there will be many, many applications for it that Flash can't fulfill.
Clearly you are proof it doesn't *always* work, but I believe I already covered the counter-examples.
Guns don't kill people; Physics kills people! - John Lithgow as Dick Solomon on Third Rock From The Sun
Sounds like regular engineering to me!
"I made something awesome, no idea how it works, but it does - don't touch it! You'll break it!"
There are at least 12 form factors (AT, baby AT, ATX,Micro ATX BTX DTX LPX NLX Micro ATX, Mini-ITX, Nano-ITX, Pico-ITX) thatr I know of, plus numerous proprietary form factors in the SBC segment. The industry came up with those because it was useful to them to do so. Nobody forced them to and nothing stops anyone from coming up with their own form factor or proprietary extensions to existing standards. Those standards and the minimum level of interoperability are a big part of why digital technology saw such an explosion in my lifetime.
Let's look at this from both sides of the purchase: Would you want to buy a Dell tower if you knew that only Dell branded add-ons will work with it? Dell proprietary memory, Dell proprietary video card, Dell proprietary cases, Dell proprietary network cards, Dell proprietary storage and so on. We had just that situation back when I was first learning computers. With rare exceptions, hardware for a Burroughs computer had to come from Burroughs, Philips hardware had to come from Philips and so on. No single OEM aside from maybe IBM, could really achieve economies of scale, all the OEMs R&D was restricted by the need to not infringe on patented good ideas from other outfits. Shit was expensive, shit didn't work all that well, shit was difficult to adapt to user needs and it was hard to make shit talk to other shit reliably. Through sheer size, IBM managed to dominate the market and some of the early desktop standards were explicitly "IBM compatible"
On the manufacturer end, being able to use an existing hardware standard also means they are more likely to be able to use standard software implementations as well. That speeds development time and reduces R&D costs. Why re-invent the network stack, possibly introducing your own failure points, when there is already a very good, exhaustively examined and tested standard? If you make sounds cards (or these days, dedicated sound processors for inclusion in someone else's motherboard) do you really want to have to develop to meet 20 different hardware standards to match every mobo manufacturers proprietary designs, or would you prefer to just develop to the PCI standard and be able to make one device that works for almost everybody?
Finally, proprietary motherboard designs are still alive and well in the industrial/embedded segments and in laptops and other mobile devices. There the form factor is constrained by physical environment and case packaging concerns, not meeting form factor standards. What IS still being develop to standard in those markets is the interfaces. Most notebooks use the same sorts of ram, albeit with a different size and pin count, as desktop machines. They still do standard ethernet, bluetooth and so on. Also, as far as I know, Big Iron (mainframes and other very large scale computing solutions) is still largely proprietary.
I need a wheelchair van for my son. Help me get the word out. https://www.gofundme.com/wheelchair-van-for-jj
If RAM held its value, there would be no need to have a distinction between RAM and "Disk". Computers would boot far faster. Databases would be right on the memory bus, with no need to "sync" to reliable storage. Many, many applications and services could be faster, simpler and more reliable.
The Machine
IBM i
I'm pretty sure there's a lot more examples of prototypes and concepts, too.
Ezekiel 23:20
You know that system that is behaving badly and just seems to work again the minute you reboot? That might not work if engineers get non-volatile RAM to work really well. Everything will be in memory with no need to load it off disk. But those slow memory leaks, weird data corruption bugs, or software that stops working when it gets into a certain state; will not just magically disappear when you reboot!
The last recorded words of the human civilization will be: "Wonder what happens if we push this button?"
We already avoided this fate once. Some of the smartest people in the world worked on creating the atom bomb but even they were a little concerned that the bomb might set off a runaway nuclear chain reaction in the atmosphere on detonation and kill everyone on the planet.
No one knew how vacuum tubes worked when they started playing with them. In fact, the first tubes pre-date the discovery of the electron; and thermionic emission is how tubes work. But once they figured it out....hoooo boy here comes your electronic revolution.
Every day we use things that work despite the fact that we, as individuals don't know how or why they work.
What's really scary is the number of medicines which fall into this category.
Heck, we don't even completely understand how aspirin works.
#DeleteChrome
The last recorded words of the human civilization will be: "Wonder what happens if we push this button?"
My money's on "hold my beer!"
#DeleteChrome
Every day we use things that work despite the fact that we, as individuals don't know how or why they work.
Every day we rely on gravity and yet nobody knows how that works. We live in a universe that we do not fully understand and possibly never will. Understanding something often helps us to find a way to exploit it to do something useful but, as you said, it is not required.
There is no mass, the difference between matter and light is not mass:
1. Light's has no mass
2. If matter is completely made of the same stuff light is made of, it has no mass either.
Mass and energy are the same thing. Light has energy.
Citation: E=MC^2
We have memories that we don't know how they work, perhaps they will be a good fit for quantum computing where we only probably know what they are going to do.
Starships were meant to fly, Hands up and touch the sky - Nicky Minaj
Sadly, you're probably correct insomuch as anyone on /. who cares about such things already knows this stuff is going on. So those who don't care will skip it and those who do care *may* skip it, or at best skim it because I'm preaching to the choir...
I need a wheelchair van for my son. Help me get the word out. https://www.gofundme.com/wheelchair-van-for-jj
The most exciting phrase to hear in science, the one that heralds new discoveries, is not 'Eureka!' but 'That's funny...' Isaac Asimov
The Machine
IBM
I'm pretty sure there's a lot more examples of prototypes and concepts, too.
https://en.wikipedia.org/wiki/...
Perhaps especially in the field of medicine and pharmaceuticals, there are plenty of products that we see working, but nobody knows exactly how.
Wikipedia has an entire category for just that:
https://en.wikipedia.org/wiki/...
In fact, I used to joke that the Physician's Desk Reference (standard Reference book for Pharmaceuticals) could be printed on two sides of a piece of letter-sized paper if they just reduced the phrase "The exact mechanism of this compound is not completely understood." to a single symbol...
Every day we use things that work despite the fact that we, as individuals don't know how or why they work.
What's really scary is the number of medicines which fall into this category.
Heck, we don't even completely understand how aspirin works.
See my post on this point:
https://science.slashdot.org/c...
I think there's a lot of interesting things that a single non-volatile memory space (today's RAM + storage) could do.
The first thing that comes to mind is there's almost no difference between the computer being "on" or "off" -- in theory, powering off is just stopping execution. There's no programs to shut down or information in RAM that needs savings. This could make power management very interesting.
You could also have as many programs "open" at once as you wanted, limited only by the amount of NV storage you had -- you'd never close them, just stop executing them. In theory you could even transfer them to another machine through some other storage mechanism in their existing state.
Operating systems might need to gain some kind of new soft reboot capability that allowed them to perform the kind of housecleaning/reset that a "reboot" does now, but in a way that didn't actually require the computer to reboot. The same with applications, a means to "reset" an application to a new-launch state which is ordinarily obtained through the boot process.
But those slow memory leaks, weird data corruption bugs, or software that stops working when it gets into a certain state; will not just magically disappear when you reboot!
Obviously the boot monitor will clear RAM and retry on a boo failure. What you apparently don't know is that existing DRAM is in an indeterminate state when powered up, and it has to be cleared before use anyway.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Proprietary-format motherboards do still exist, but they are vanishingly rare compared to how they used to be. Back in the early days of the PC you were super lucky if you could swap motherboards between brands. But then the clones came along and they all used the pattern from either the IBM PC and XT, or the IBM AT, and that began a sea change in the PC industry. It wasn't until ATX, however, that those proprietary motherboards became rare.
Today, it's actually typical for SFF PCs to use a standard-size motherboard, albeit one of the smaller standards. Only the most expensive and fiddly SFF PCs (and NUCs, of course) use a custom mainboard.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
If RAM held its value, there would be no need to have a distinction between RAM and "Disk".
Only if RAM were also as cheap as storage. We still use different kinds of RAM in the same system because even RAM isn't as cheap as RAM, depending on what kinds are involved. There's L1 cache, L2 cache, maybe an L3 cache, system RAM, peripheral cache RAM... and they're all different types of memory, sometimes subtly and sometimes dramatically.
In a world where everything has the same cost, you'd be right. But we don't live in one of those.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
IPAQ and other WinCE devices of its generation had nonvolatile storage because flash was expensive at the time. It actually turned out to be a horrible decision because a lot of users lost a lot of data and subsequently lost a lot of confidence in Microsoft. But they also had flash slots because volatile storage only fits the needs of casual users. I had a Sandisk combo WiFi+128MB CF in mine. That left the RAM free for applications, and stored my data where it wouldn't evaporate if the battery drained.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Some of us read it in full. Thank you for taking the time to compose a well-thought-out post.
You describe a thought experiment in which terrans define space as coordinates from inside space, then identify mass as bending that space to cause gravity; while martians define space by the path of gravity, in which mass doesn't bend space. Then you say that both of these can't be true, thus the terran explanation is impossible.
That's a blatant equivocation fallacy. Your resolution of this fallacy is akin to if I cut a tree branch and call it a meter, and you have an iron bar you call a meter, and these two things aren't the same length, thus you must be wrong. The problem is your thing is a meter and my thing is a yard.
Support my political activism on Patreon.
Second-level memory is generally randomly-accessible memory.
Support my political activism on Patreon.
What you apparently don't know is that existing DRAM is in an indeterminate state when powered up, and it has to be cleared before use anyway.
Kind of. RAM stays wherever it is at the time; the OS will wipe each allocated page on allocation.
Support my political activism on Patreon.
The last recorded words of the human civilization will be: "Wonder what happens if we push this button?" ....
We already avoided this fate once.
Once?
9 times the world was at the brink of nuclear war — and pulled back
https://www.businessinsider.co...
Can't be. All modern systems require NOSMOKE.EXE compatible memory.
Two votes, nice post.
Thank you for doing so and for letting me know. But I'll bet you one free Internet that most of the issues I raised were things you were already aware of.
I need a wheelchair van for my son. Help me get the word out. https://www.gofundme.com/wheelchair-van-for-jj
damn, my inline quote stuff got lost in the posting. I must have done something wrong. The "motherboards blow..." bit is a quote from the parent post.
I need a wheelchair van for my son. Help me get the word out. https://www.gofundme.com/wheelchair-van-for-jj
They naysayers said that about the LHC causing a black hole and destroying the world. There is always going to be someone who thinks the worst.
There are three kinds of falsehood: the first is a 'fib,' the second is a downright lie, and the third is statistics.
This article was talking about a process that works but those studying the process did not know WHY it worked. When the first atom bomb was detonated the people who built it knew how the bomb was supposed to work in theory but there was still some doubt about other possible outcomes.
"9 times the world was at the brink of nuclear war" It is probably been more than 9 times but there are no unknowns or doubts about the damage a nuclear bomb would produce.
The scariest scenario we face today comes from bioweapons. It takes far less resources to create a bioweapon when compared to building a nuclear weapon. And countries around the world are creating bioweapons in order to create countermeasures. We are one laboratory screwup or one demented scientist away from having to battle the walking dead.