New RAM Based On CD-RW Film On Horizon 103
SiliconShaman writes: "Ovonyx Corporation is reporting initial success at producing a very cheap non-volatile RAM. Supposed to be cheaper, faster, etc. than conventional Flash memory. Applications include satellite and aerospace, cell phones, the list goes on. Details can be found here: Short Technical Presentation in HTML." "OUM memory technology," says Ovonics' Web site, "is similar to DRAM and many orders of magnitude faster than Flash write." The proliferation of devices which will need copious nonvolatile memory should mean a healthy market if this technology reaches the production line. I know my camera could use some more storage ...
Re:Interesting stuff. (Score:1)
Hmmm... go to the store and you buy a 50GB HD. Go home, partition disk as swap, pull out your old (outdated) RAM chips, now you've got 10GB of memory running at RAM speed (see above)
Re:FIRST (Score:1)
Not _QUITE_ vaporware... (Score:2)
Re:Kinda tough (Score:1)
This is a Good Thing (Score:4)
Will your memory wear out? (Score:3)
Of course, most bits won't see this kind of punishment, but I can imagine data acquisition apps that might trash a few bytes of storage within a year or two or ten. Hopefully the machine's L2 cache would effectively rate-limit writebacks to main memory, but it should still be possible to set up an aliasing situation that would cause a line to be flushed on every write.
It's NOT CD-RW! (Score:2)
Thank you.
Re:Is there a good tool for extensive testing of a (Score:1)
NAME
badblocks - search a device for bad blocks
SYNOPSIS
badblocks [ -b block-size ] [ -o output_file ] [ -s ] [ -v
] [ -w ] device blocks-count[start-block]
DESCRIPTION
badblocks is used to search for bad blocks on a device
(usually a disk partition). device is the special file
corresponding to the device (e.g
is the number of blocks on the device.
+++ATH0
"just a few additional layers"... (Score:2)
Furthermore, in order to catch on, the product has to be compatible with existing systems and be either a lot faster, significantly cheaper, and/or come in much higher capacities; otherwise, they are not going to catch up with the economies of scale of flash memory. If they can do that, I think there is a market: non-volatile, fast storage is useful in more and more applications.
(As an aside, they are not talking about optical storage, they are talking about taking advantage of electrical properties of materials that are ordinarily used for optical storage.)
Re:RAM (Score:1)
Re:RAM (Score:1)
Re:RAM (Score:1)
I can't seem to remember that one. Was that the Dynamic Transient Magnetic Re-allocation Policy of my hard disk [ntk.net] or the transient hysterisis loops in the head media [ntk.net]? If it's the Re-allocation Policy of my hard disk, then I'm fscked, cuz I didn't do those backup things that everybody said I should do (but my AOL should back up important things, right? It said that it would make sure that I had an excellent browsing experiance!). If it's the transient hysterisis loops in the head media, then I already tried the reasonant magentic distortion rectifier. But I didn't really have one after you told me to use the 'highly-acidic battery charge' on the supply cabinet while they were plugging in the new networking room, so I just used the hammer and screwdriver, like last time. But now my hard drive is sort of bent and part of the metal box broke, and now that floppy circly thing is hanging out. And the AOL tech support people keep hitting the 'mute' button on their microphones for long periods of time after I call them and tell them what I did. It's almost as if they're laughing at me. But AOL wouldn't do that, right? Right?
proofreading (Score:1)
Re:May be serious. (Score:1)
I was thinking the same thing (re: Transmeta). Low power processors, low power ram, plus the possibilities of replacing the hard drive (which requires power to stay spinning) could make for a very energy-efficient box.
Hell, as long as we are dreaming, why not some of these long-promised, low-energy color flat-panel displays! =) Mmmmm... a laptop that runs for a week on one recharge...
Re:OPEN SOURCE RAM (Score:1)
Perhaps osm and Miss. Portman as Captain Kirk and Yeoman Randall in 'Star (as in hot young actress) Trek'? Or Scully and Mulderin 'OS/X Files'? ESR could star as Cancer Man!
Re:Kinda tough (Score:1)
Re:The most supreme sound ... (Score:1)
Re:One Possible Use (Score:2)
Hey now, Macs have their own share of problems..
Re:One Possible Use (Score:1)
for this to be really effective you'd need multiple layers of backups so you could choose the state most trouble free. on the other hand, you'd be restoring the ram to the state it was in JUST before a major crash--not a very comforting state of affairs.
A more promising situation would be using the stuff to store ram so that a power failure would not result in catastrohic downtime for rebooting. again, this would be more applicable to windows. but i'm getting tired of waiting for my linux and bsd boxen to boot up after i power them down (which I do a couple times a week so i don't have to hear the fans, or so I don't have to pay the giant boston edison bill).
But there is nothing special about OUM as NV storage--that's what hard drives do best as long as you don't have size/power/price/portability constraints.
Don't laugh, my other .sig is a porsche!
Re:May be serious. (Score:2)
IIRC, in most cases the cache only mirrors what's in the main memory, so it wouldn't be a problem. However there would be 2 other issues.
Firstly, booting would write over part of the memory - you'd have to tell the OS to recover, unless that's what it did all the time. You could have a reserved area for booting, then the system looks at the main memory and recovers.
The other problems is saving the entire state - you know the memory, but not what was going on in the processor, network, etc. when the thing goes down. So some things will be unrecoverable. And of course if the thing really crashes it won't help without some pretty serious recovery tools.
Re:One Possible Use (Score:1)
Voila! You're back, 0.5 seconds before you crashed, with an identical stream of code and data coming... so you crash again!
Your blue screen of death just flickers REAL FAST. See loop, infinite.
Now, if there were some smarts that could trap and diagnose the cause of the crash, reload the memory, fix the problem, and THEN restart things... you'd have something.
Hmmm... sounds like something the High Availability folks could look at....
Re:"2-D" holographic memory ? (Score:1)
Context state saves and RAM in a versioned CPU (Score:2)
Perform the copy CPU register state and RAM image to secondary RAM in hardware as an atomic operation which occers once per clock tick -- if possible, by some subdivision otherwise. From then on copy only deltas between any two states in the rest of secondary RAM like most versioned filesytems. The number of potential versions stored is limited to the size of secondary RAM and the amount of change over time, like any other cache.
It's a pretty cool idea... anyone know if some exotic hardware with these kinds of capabilities has ever been tried?
Re:May be serious. (Score:4)
AmigaOS, or should I say Kickstart, partially implemented recovering memory state after reboot (yeah, and this was done way back in 1985.) After rebooting, it wouldn't erase memory, but the OS would look for some system vector tables and do some basic sanity checks to see if the tables are corrupted. Some nice uses were for example a RAM-disk that could survive rebooting.
Sometimes the system hanged in repeating crashes and reboots, though. Then your only option was to really erase memory, for example by toggling The Most Significant Bit (ie. power switch).
Other bad point was that also viruses liked to hook themselves to those vectors, enabling them to survive reboots.
For the rest of the state, maybe you could log some state changes to for example display adapter, network card and etc. Or maybe your devices would have to expose their internal state in some compact structure you could just copy to log areas periodically (when the system would be in special recoverable state.)
I don't know. :)
DMCA Violation (Score:1)
Re:Ten trillion write cycles? (Score:1)
What consumer devices are you going to have that are going to be generating data at the rate of one million items per second?
Re:Interesting stuff. (Score:1)
It would also be kind of silly. If you had a device that was as fast as RAM, it should be addressed like RAM, not swap. The point of swap is to be a storage area for programs that don't currently fit into memory because others are loaded. So instead, the OUM should be used by the system the same way as normal RAM, instead of as swap.
Getting closer.. (Score:1)
Re:OPEN SOURCE RAM (Score:1)
And who says I'm an armchair troll
Perhaps I'm a closet troll and not just a 'karma-whore'...
Besides, osm and Miss Portman are yours to do with as you like (literally), and it wouldn't be my place to do an osm troll..
The difference is thoroughness vs. speed. (Score:2)
The distinction is probably very similar to FORMAT /Q (QuickFormat -- just rewrite the FAT), and FORMAT /U (unconditional format). The former rewrites just the FAT table, with the presumption that the media has not grown any defects. The latter reformats the entire media, thereby "Refreshing" the sector boundaries (if a floppy) and possibly identifying any grown defects.
In the case of a CD-RW, I'd imagine performing a full-blank gives you a marginal increase in recording quality (ie. you're more likely to get a good, clean "burn" subsequently), and it may possibly identify defects (such as scratches) during the erase. Not sure.
--Joe--
Re:Questions - (Score:1)
Here's how it works: you surround the memory with a conductive metal; it's really that simple. external electric fields can only get inside if there are holes in the enclosure. this is why you wouldn't be able to pick up radio signals if you were inside a metal box, or why radio signals would sound really really weak if you were inside a giant birdcage. (incidentally, this is also why a car is a safe place to be in a lightning storm)
so, you just make sure to wrap some foil around it, and then the memory's only vulnerabilities are through the connection it has to the rest of the components.
as for magnetic fields, I'm less sure but I think external magnetic fields can be shielded from by an iron (because iron is ferromagnetic) enclosure.
someone with better physics knowledge correct me if I'm wrong?
AHA! (Score:1)
- Steeltoe
In time, everything will be revealed.
Re:Some Background on this Company (Score:3)
I am not sure that NiMH batteries were invented by ECD. The ECD website only claims a) all "significant" manufacturers of NiMH have a license with them (implying that some don't - why?) and b) the first commercial NiMH manufacturer 'used' Ovionics technolgy. This company (Gold Peak) was also 'one of ECD's early licensees' -- this seems like an odd way of saying "we invented NiMH". It is almost as if they are trying to imply that without actually saying it
I tried checking the USPTO database, but if he had the groundbreaking patents, they are too old to show up on the database. I concluded this by checking the bibliographic entries for current Ovshinsky NiMH patents (which contain the patent numbers of preceding/related art) I presume he would cite his own groundbreaking patents. It is possible that I'd learn more by reading the complete applications, but IANAL (and no one's paying me for *that* depth of research)
I was aware of their early flexible amorphous solar cells in the 70's, but I didn't know these were a major part of today's market. Are they?
Besides I'm not sure that one major product (or maybe two) in 40 years is a "decent track record in products" (ECD was founded in 1960) ECD seems to have some viable products, but I'm surprised that they seem to be incremental improvements over the state of the art, while their past (and present) technology always seems billed as 'revolutionary'
Of course, that can happen. I think Harry Bede is a good example. He designed and produced the BD-5 airplanes and an interesting 'inline' automobile -- both products I'd have bought instantly (well, once I could afford them) but his companies can't seem to stay in production very long.
_____________
ALWAYS listen to AOL! (Score:1)
If AOL didn't back it up, it wasn't important d:-)
- Steeltoe
Interesting stuff. (Score:3)
I'm a little curious, though, whether this is best suited for compact applications like flash RAM, or as a means of replacing both RAM and fixed-disk technologies. If the size reduction is substantial enough, and it's as fast as RAM, it's possible that a system might ship with a single fixed rotating rewritable drive (like a hard drive) using OUM technology to provide a significant chunk of storage space (say, multiple gigs) with high access and transfer speeds. Imagine your swap partition running at the same speed as your RAM. That'd be pretty spiffy.
--
Power Efficiency? Life Span? (Score:1)
Also, I know that most flash devices have a limited number of writes they can perform before failure (a large number, I'll admit). Is this a worry with this technology or not?
Most of the small devices that would be using this technology would require both of these things.
speed will be the issue (Score:1)
I bet they'll be a few orders of magnitude slower than conventional electron-based storage since the bits are stored by using atomic phase changes, which are much slower than the speed that electrons can zip around.
Jeff
Pricing? (Score:1)
Re:Context state saves and RAM in a versioned CPU (Score:1)
I am not aware of any hardware that does this, but I saw a very interesting-sounding software package at an event last year (Fall Internet World?) that does something like this. I really, really considered buying it! (-8
Is the device to read/write this stuff going to be independent of the medium? So it could come in PC-Cards, 3 1/2" diskettes, RAM, EPROM form factors, etc.? If it's durable and has good resistance to heat, movement, etc., it might be perfect for the wearable PC I keep trying to design (but I can't keep up with all these innovations it would be great to incorporate!).
Re:RAM (Score:3)
For example if I have SDRAM (64 bit bus) PC133 10 ns memory with bandwidth of 1.06GB/s and RDRAM (16 bit bus) PC800 20 ns memory with 1.6GB/s which ones I can interleave to get memory with latency of 12 ns and bandwidth of 4GB/s (256 bit)? (I have really no idea of real latencies of those memory types and it hugely depends how you measure it - time it takes for chip to read bits or processor to receive required bits. But what I know is that SDRAM has much lower latency)
I'm not aware of motherboards supporting SDRAM interleaving but Intel already does this with RDRAM in its new mobos so it should be possible. I think that this is because SDRAM already provides enough bandwidth in most cases.
Note that when using DDR SDRAM you can double the bandwidth (for SDRAM) and one can only wonder why is/was Intel trying to push something like RDRAM into market?
For those still wondering the answer to second paragraph I will give a hint: you cannot reduce latency with interleaving.
_________________________
Ah, the irony (Score:1)
Re:Some Background on this Company (Score:1)
At only 10 trillion cycles, it won't do for cache (Score:1)
Cache width 4 bytes at a time.
I guess these are conservative estimates:
10*10e12 / 200*10e6 * 5 * 256*1024
16384000000 seconds it would last,
ah, that's 532 years. OK, no problem
OTOH if it's only as fast as DRAM, it isn't good enough for cache. invalidating the cache (thus refilling it) after a power-on doesn't really seem a problem to me.
Re:Power Efficiency? Life Span? (Score:1)
--
"2-D" holographic memory ? (Score:1)
Smells like FRAM (Score:1)
http://www.edtn.com/story/chipw ire/OEG19991207S0006 [edtn.com]
Storage choices (Score:1)
Oh well, at least we won't have to rely on Scotch tape [slashdot.org] to hold our data....
cdrw media ram (Score:1)
Also if a media could be developed that could be made semiconducting you could make erasable processors. That could have some interesting aplications.
One of these days... (Score:3)
Look at the curves. (Score:2)
What that number means is that they only TESTED it for a few months. B-) If you look at the curves, they were showing no sign of curving. So there's no indication that it would stop working after 10 trillion, or even 100 quintillion.
Read another foil, and you see that read is CONstructive when it's in the high-conductance state, and "the current is negligable" for the low-conductance state.
If there's any destructive effect, it would be the read current in the low-conductance state gradually coaxing the device to grow a crystal across the boundary and switch to the high-conductance. But even if you hammer on the bit that won't happen for at least four months.
So even if that turns out to be a problem, you could treat it like a dynamic RAM that has to be refreshed ONCE every FOUR MONTHS. B-) Much better than silicon DRAM that needs a refresh a thousand times a second or so. Kick off a cron job three times a year to refresh your RAM.
Do that and it looks like it could last until the rest of the computer fails from diffusion of impurities through the silicon.
Electronics and memory (Score:1)
Seems Quite Good (Score:1)
What a coincidence. B-) (Score:2)
If you'll read all the foils you'll see they licensed the amorphous switching element from one of his companies (which is using it to make CD media.)
Another successful product from him is the flexible amorphous solar panel. Three layers of amorphous solar cell (intercepting three different bands of sunlight), electrically in series and grown on a stainless steel base.
Because it's amorphous it can be bent quite a bit without breaking (though it isn't quite as efficient as crystaline cells because there are more sites where carrier-pairs can anhialate rather than giving you current).
You see 'em on boats all the time. I've got one tied to the cabin-top on mine, keeping the battery up when the boat sits for a while. (On a previous boat it was the only thing charging the 85 AHr deep-cycle battery, which powered the radio and lights. It could bring the battery from 25% to full charge in a couple weeks. We never needed to hook up the charge circuit from the aux engine.)
Persistent OS'es (some random thoughts) (Score:1)
If this becomes available, EROS [eros-os.org] and other persistent OS'es would be easier to develop and/or better fitting to available hardware?
If these things were in 10-100GB class, maybe we could unify random access memory and traditional more-or-less persistent storage (read: hard disks). Especially considering 32bit addressing is being left behind, so you could simply have it mapped to memory.
On the other hand, that annoying javascript scroller on their front page seriously damaged their credibility in my eyes. Also, keeping in mind, most of these 'revolutionary storage technologies' never see day of light.
Read about it here. (Score:2)
Read the foils from the presentation of the research report here [ovonic.com].
It gives far more detail than I've ever seen for an announcement of any other memory technology. B-)
Ten trillion write cycles? (Score:1)
Um, I don't think that will work for general purpose storage. One million memory accesses per second is not unrealistic. At that rate, your OUM will wear out in about four months. Wouldn't mind a few GB of it in my handheld MP3 player, but I'll take volitile memory for my system, TYVM.
--
Answers (IMHO) (Score:2)
The conductive state is a (poly?)crystaline material that shorts two electrodes.
The resistive state has a region of amorphous (glassy) material in the space between the electrodes, surrounded by the remaining material which is still in the (poly?)crystaline state.
Writing it consists of MELTING the region between the electrodes, leaving it either cool enough that it solidifies quickly into the amorphous state, or hot enough that it solidifies slowly and the crystals grow into the melted region as it freezes. Think frost on a window in the winter.
(Of course at these scales, even "slowly" is measured in nanoseconds of elapsed time.)
Charge carriers from particles won't make significant increases in current in the glassy state, or remelt it and let it crystalize. Particles might disrupt SOME of the crystaline conductive state - but there is a LOT of it in parallel. By the time enough raidation hits it to increase its resistance measurably the rest of the components in the computer will be approaching the "sand" state.
Think about trying to use radiation to disrupt a wire until it won't conduct, or a glass bottle until it will.
2. What effect will magnetic forces (and/or electro-magnetic forces) has on this type of memory?
It isn't made of magnetic material. (Again, think of using a magnet to disrupt a copper wire until it stops conducting, or a glass bottle until it starts.)
If you put a big enough EMP into such a chip you might generate enough voltage and current to write the bit. But you'll probably fry both the static protection and the components in the pad driver/receivers on the chip's terminals with much smaller EMPs, because the interconnect wiring is a much bigger antenna.
It's still the frame rate. (Score:2)
Is there anything else such as applications, server services (ftp, http, nfs, etc) or non-games that I can see the performance increase in?
When I said "frame rate," I didn't necessarily mean first-person shooters. I could have meant radiosity raytracing frame rate in a m****n p*****e studio's rendering farm (T*y S***y 2 took nearly forever to render). And there's always SETI@home, distributed.net, and that new one [processtree.com] that pays you for your MIPS.
SmartMedia aesthetics (Score:1)
"If it works, and can be used as a replacement for DRAM and Flash, I can't think of anything to stop them from making SmartMedia and CompactFlash cards with OUM technology inside them. And if it stores more data in the same space, that'd be a pretty nice feature for digital cameras, too. Keep the interface pinout and form factor and all that the same, just replace the storage innards."
You said it!
I like smart media's shape and size; besides that, my Leica Digilux uses it, so for better for worse I am stuck with it at present for happy reasons. (the digilux, same as Fuji model, what, D-700?, is really nice).
I don't like the sony memory sticks, CF is still much bulkier even though the capacity goes much higher, I don't want to trust a floppy drive like on the mavicas and certain others
if this stuff can raise its capacity, I am all for it.
timothy
Re:RAM (Score:1)
Hmm.. what an informative title. Can we get something a little longer, next time?
I'll give you a few hints and leave you to it: magnets and optics. Enjoy!
This didn't work for me. I got the case off of the computer, yanked the newfangled RAM thingy out (that little clipper thingy snapped right off, landed on that noisy dusty box right in the middle) and stuck a magnet in. Nothin happened, cept my screen got all weird and frizzled and colory (I forgot to turn it off, but it didn't seem to make much difference). My AOL login screen got all screwed up. So I yanked the magenty bit out and stuck it back onto my box of floppie disks (gotta hold em down somehow).
The optics thing didn't werk either. I went to the network room of the office and yanked out some of that orange optical fibur cable from the big gray box in the middle of the room, and then cut it open. I yanked out the little thingy thing inside and jammed in into the RAM socket. That seemed to work, so I put the lid thing back on the computer boxie and started clicking on AOL, but it was slow and stupid, not faster. You stupid Slashdot person screwed up my computah.
I am suspicious (Score:1)
performance numbers nor does it have any specifics. It sounds plausible, but I would be very cautious in believing this, unless I
had seen some real results published, such as from the ISSCC or something. I mean, you look at what the
RAM manufacturers show at these conferences, die photos, highly specific performance numbers, process details, etc. And contrast it with the
fluff in this article.
It certainly looks like a great promise, and
what they say is true - trench capacitor DRAM
technology is an unholy mess for processing,
but you have to be a little skeptical in this
industry, if there is nothing but
a press release to believe.
I'd become fluent at reading that type of writing (Score:1)
other useless skills..... *shrug*
Until then.. it's just pops and buzzez...
(static in my ear) *shrug*
Re:Ah, the irony (but hey, it might help!) (Score:1)
Which is part of the reason I'm only buying Compactflash Type II peripherals... So when I can afford a Microdrive, it'll work with what I got. =P
Some Background on this Company (Score:5)
Though I can hardly blame
Sure enough, on the "About the Corporation [ovonyx.com]" page, it confirms: "The Corporation Ovonyx, Inc. (Ovonyx) was formed in 1999 as a joint venture between Energy Conversion Devices, Inc. (ECD) and Messrs. Tyler Lowrey and Ward Parkinson. ECD is Ovshinsky's company (founded in 1960). Surprisingly, no link or further information is provided on ECD, which according to the Ovonyx Corporate page "has been actively pursuing phase-change material and device structure development,optimization and characterization for many applications - but principally for optical and electrical memories."
From what I recall from the 70's/80's, ECD wasn't 'focused' in these areas, but on solar panels (hence the name "Energy Conversion Devices"). This may explain why "ECD's contribution to the Ovonyx joint venture was all of its intellectual property (IP) in this area" [optical and electrical memory]. Perhaps ECD didn't feel it could make use of this IP, and turned it over to two former top Micron Technology (chip) execs. Read on for details
THE BACKGROUND
Ovshinsky was a darling of the Japanese in the 70's/80's when Americans were in shock because the Japanese were using American findings like the management theories of Edwards Deming (who was revered like a god in Japan), 'process control', and "just in time" to turn out cars that the US auto giants couldn't match. American business was also awash in culture shock from dealing with the Japanese business systems (kureitsu, etc.) as equals and as a potential market.
Ovshinsky raised money by chiding US corps that they would miss the Next Big Thing if they didn't invest in his work, but his primary business relationships were with the Japanese.
The PBS show NOVA even did a one hour documentary on him ("Japan's American Genius" 10/27/87) that seemed to promise that cheap high efficiency amorphous solar cells would be around any day now. I've kept my eyes peeled ever since (I instantly made the Ovonyx connection in 5/2000!), and never heard anything about ECD. The advances in amorphous technology always seemed to come from elsewhere.
I haven't been impressed by ECD's ability to bring *any* product to market in 40 years, and I don't know of any breakthroughs they have made or licensed -- and all their 'background' and 'product' links seem to point to nonexistent documents in a 'drafts' folder. However, I may be wrong, or perhaps the documents are being updated, so I refer you to ECD's home page, which is (perhaps unsurprisingly, considering Ovshinsky supposedly pioneered 'ovonics') http://www.ovonic.com [ovonic.com] not to be confused with the OVONYX [ovonyx.com] site in the
Perhaps I am a little jaded, because I was once a big fan of Ovshinsky (as he was presented), but what I've read in the OVONIX and ECD (OVONIC)web sites seems to have an unusual, almost Microsoftian degree of 'spin'. Caveat emptor.
However, if anyone out there knows of some concrete product or technical advance that proceeded directly from ECD or Ovshinsky, I would be *most* happy to hear about it. You have to reclaim those childhood heroes when you can! It's good for the soul.
_____________
Questions - (Score:3)
Questions -
1. What effect will this type of memory
device has under radiation bombardments?
If this memory is to be used on spacecrafts, it has to be able to withstand radiation bombardments.
2. What effect will magnetic forces (and/or
electro-magnetic forces) has on this
type of memory?
If this memory is to be applied in miniature appliances, the chances that these appliances be in contact with (or being put next to) magnets or under magnetic fields is very large. So, will the amorphous (disordered atomic structure) and crystalline (regular, highly repetitive, and ordered atomic structure) stage be reversed/change/effected due to the magnetic effects?
We do have to be concerned with the effects, because we just do not know what this type of memory device will ultimately be used on - it could be used on embedded devices to control anti-lock brakes on cars, for example - and if the memory device is "affectabled" by either magnetic or radiations, then, this type of memory device should not be used to power computers which controls critical functions that may affect the safety of human lives.
This is just my humble 2 cents.
Re:One Possible Use (Score:1)
Would be damned handy for debugging though...
I don't understand exactly you think this (Score:1)
Re:May be serious. (Score:3)
That's only half true. The cache holds a copy of what should be in RAM. There are two possible common scenarios:
The latter form of cache performs alot better, for a couple reasons. First, writes to memory are slow and a write-through cache doesn't hide them. Second, alot of writes are redundant or can be combined with other nearby writes and a write-back cache serves as a filtering and combining mechanism. The drawback is that the cache has a different picture of memory than the external memory has.
Anyway, the way you do "recovery" is to checkpoint the OSes state every so often (like, say, every timer tick when you do a task switch). You can save all the registers, flush the cache, and checkpoint off to the OUM. The device issue you mentioned is solved in a similar manner to APM, I'd imagine (not that I know the solution, but I'm saying it's a familiar problem that's already being attacked).
--Joe--
Chips. (Score:1)
Re:Some Background on this Company (Score:1)
Then I reliazed that if they didn't have licence agreemants with all the NiMH manufacturers, maybe the patent wasn't so critical. I read some posts this year saying how the big Japanese companies all have tons of cross-licenses. (was that you?)
Your right, there's alot of spin on those websites -- pretty sneaky!
No, put a bluetooth tranceiver in your skull (Score:1)
Re:CD-RW film as a fast read-write media (Score:1)
I would think that no matter how fast of a phase change they can manage, they're still going to have a lot of delay doing the blanking.
But they don't use the same technology (laser) as in CD-RW/DVD-RAM optical disks but a transistor for every single data bit. That would mean that they do not need to blank the entire ram (or entire blocks of it) to reuse it.
Or did i miss something in the technical description [ovonyx.com] of the OUM, where they also mention that every single bit can be uniquely addressed for read and write?
They are not the only company in this market (Score:2)
Some clarification:
- They dont use RW "Film". Their IC will just contain small amounts of a similar ternary alloy. (Ge2Sb2Te5)
- Writing to the memory cell works by heating it with an electrical current !! Temperatures in excess of 600 degress celcius are required for a phase change. It seems that this is the main problem with this kind of memory.
- Reading is done by measuring the resistance. No refreshing or anything similar required.
- They dont have a working sample of a full memory chip yet. As of now it seems to be VAPORWARE
In case you want to know more than written in the short HTML marketing piece check this out:
http://www.ovonic.com/technology.pdf
However there are other companies with very interesting (and available) products in the nvRam
sector, which are trying to come by the disadvanteage of flashram:
RAMTRON: Using perovskite crystals to store data. (FRAM) Advantage over flashram: Faster , less power consumption, higher data retention.
Quite interesting: www.ramtron.com
SIMTEK: They have srams that automatically store the containing data to an on-chip Flashram when the power drops. And vice versa.
Seems a litte brute-force to me, but seems to serve its purpose well.
www.simtek.com
ZMD: Has almost the same product as SIMTEK. They just do less bragging about it:
www.zmda.com
Time and energy required to write? (Score:2)
AIUI the reading is done by simply measuring the resistance of a tiny cell of this amorphous material, and that would be pretty fast and easy. But writing to it requires a phase change induced by heating. That sounds slow and expensive by comparison.
Add this to the problem of the memory "wearing out" after a few weeks of being toggled at 10MHz and it looks more like a replacement for Flash memory than for DRAM.
Nevertheless, it sounds pretty cool.
Paul.
RAM (Score:3)
My tech friends are usually stunned when I pick up a stick of PC100 that has 4.5ns instead of PC133 at 5.5ns - they say "PC133 is better!".. and nevermind why. Alittle arm-wringing and explanations of latency and what cache hits v. misses do to their processor performance usually helps. For the stubborn, I ask them to bring their "PC133" ram over and we run a Quake demo. Guess who wins?
I don't want to hear about how much more RAM the industry is capable of making - I'm interested in hearing how fast they can make it. Bandwidth * Latency = Performance.. you cannot have high bandwidth and HIGH latency and get good performance - we've used up all our tricks in that area.
That being said, there are alternatives underway. I'll give you a few hints and leave you to it: magnets and optics. Enjoy!
One Possible Use (Score:2)
All you'd need to do is have the RAM written to the OUM every few minutes (or even seconds). In the event of system lockup, the hardware can clear the memory and write the OUM backup back into RAM. Voila! You're back where you started (more or less).
Of course, this wouldn't be necessary for anything except Windows machines....
Re:Does Faster RAM Noticably Increase Performance? (Score:2)
Why should I care about and/or buy faster RAM?
Two words: Frame rate.
COOL (Score:2)
However, unfortunately, due to the fact that devices of this nature could conceivably store illegal copyrighted materials, the DMCA precludes this technology being made available in the US.
Re:Will your memory wear out? (Score:1)
If this stuff has more writes than flash and is faster than flash, then it has great potential as a successor to flash.
Re:Power Efficiency? Life Span? (Score:1)
Did you read the article? Right next to the pretty graph it says:
"Further, Flash memory 'wears out' (fails) after 100,000 write cycles, while the OUM memory state can be written more than 10 trillion times..."
Not holding my breath (Score:1)
May be serious. (Score:4)
Very cool stuff, especially for laptops. You could selectively power RAM to save a few watts here or there. The only problem I see with a system with nothing but non-volitile RAM is filling the cache inside the processor. Easy to fix I'm sure, but if the cache was non-volitile too, you'd have the entire machine state saved.
Intel got in early - I'm sure Transmeta would be terribly interested in RAM that you can take power away from, and have it maintain state...
Re:Interesting stuff. (Score:1)
Re:RAM (Score:5)
> you cannot have high bandwidth and HIGH latency
> and get good performance - we've used up all
> our tricks in that area.
According to your formula, if you keep bandwidth constant and increase latency, then your performance increases.
Clearly, this is wrong.
How about:
Performance = Bandwith / Latency
Have a nice day.
--
Re:Ah, the irony (Score:1)
Take it with a grain of salt (Score:2)
"Patience is a virtue, afforded those with nothing better to do." - I don't remember
Vapourware? (Score:2)
Dave
Re:RAM (Score:1)
Hard drives are getting larger. Hard to aruge with that. RAM is getting larger. RAM is used to cache the hard drive. Caches are getting larger. RAM gets cached in the L1 and L2. And I don't follow that part too much, but I'm sure there are more registers now than there used to be, though I suspect that's a bit slower to change. And registers "cache" the cache. Well, sort of. You know what I mean.
So if you only care about latency, think of it this way: bigger RAM means faster hard drives. (well, this is non-volatile RAM anyway; it would replace hard drives). Wait a second, what are you complaining about anyway? Large non-volatile RAM is VERY useful. It's not supposed to replace the RAM in your computer).
Re:May be serious. (Score:1)
Wasnt't that what 'Standby' is? Swapping the RAM to HD and then cutting power, essentially?
terribly interested in RAM that you can take power away from, and have it maintain state...
Um... sounds great... until the machine crashes.. and you have to use a magnet (or bulk eraser) to reboot... well... not without an operating system, since a magnet would wipe the hard drive...
even denser storage is on the horizon (Score:1)
Re:Power Efficiency? Life Span? (Score:1)
My guess on writing is that of course it would take more power, but since they are working with a greatly reduced area, the amount of energy required to effect a state change should also be less than for CDRs. Also the shorter distance from the "write head" to the storage material should help them at least a little.
Re:Smells like FRAM (Score:1)
Re:Will your memory wear out? (Score:2)
10 trillion writes = 10^13
Maximum write rate on a PC approx 100MHz = 10^8/s
Therefore, minimum time before write cycle exhausted = 10^5s which is about a day.
Put like this, it isn't very impressive. Of course, nobody is going to write bits quite that fast with current technology. If a computer has 100Mb memory and writes byte to a random location (a major assumption) 10^9 times a second (1 GHz) then each byte changes about 10 times a second, and the memory lasts 10^12 seconds, which is 'ample' (over 1000 years.)
There may have to be some twiddling to ensure some parts of the memory don't get hit much more often than others.
Even if the lifetime is only 5 years, I can live with replacing my memory that often.
Re:Some Background on this Company (Score:5)
Ovshinsky has a decent track record in products:
Ovshinsky's big problem has always been with his manufacturing processes. Since he's just about the only player in amorphous semiconductors, he has to develop his own fab techniques. That's a big job; many billions of dollars have gone into making silicon semiconductor technology work as well as it does. ECD has to match that, working alone. They never really have, which is why amorphous transistors and amorphous ICs never took off, although both did work. (Burroughs even shipped some machines with his early non-volatile memory in the 1970s.) His battery technology also has fabrication problems. But slowly the stuff is starting to work.
Re:RAM (Score:1)
I would like to have 4 gigs of RAM in my machine.
Then at boot do a burst transfer of the first two in memory (that's the OS) and then, every 5 minutes all my data to one of the two gigs left.
Imagine: all my data and the OS in memory. And a UPS capable to last until everything lands on disk.
I WANT MORE RAM!
Re:RAM (Score:3)
If a memory has a latency of, say, 5.5ns, and is able to sustain it, then you get the speed from the following equation. 1000/5.5ns = 181MHz (5.5ns is very fast, very expensive RAM - you'll see it on those new hotshot video cards). More commonly, on PC133, you will see 7ns. 1000/7ns = 143MHz (ergo, PC133).
Nobody, to my knowledge, can even manufacture memory that fast. Even the new NVidia cards don't have memory that fast. (1000/4.5ns = 220MHz!)
More than likely, your better Quake performance is due to a more optimized system, better video card, etc, etc, and certainly not due to your main memory (PC133 is faster than PC100). Additionally, the BX chipset on PC100 is a little bit faster than the VIA Apollo Pro133A chipset on PC133 (in some cases). An overclocked BX chipset at 133MHz(!) is incredibly fast.
Re:Context state saves and RAM in a versioned CPU (Score:1)
No, but an emulator (like Nesticle) could be easily modified to do it.
They should ban books, too! (Score:1)
--
That has nothing to do with it (Score:1)
Re:Ah, the irony (but hey, it might help!) (Score:2)
When I stop to think about it, though, this OUM stuff doesn't replace a certain form factor, or a certain interface or API - it replaces a memory technology. If it works, and can be used as a replacement for DRAM and Flash, I can't think of anything to stop them from making SmartMedia and CompactFlash cards with OUM technology inside them. And if it stores more data in the same space, that'd be a pretty nice feature for digital cameras, too. Keep the interface pinout and form factor and all that the same, just replace the storage innards.
--