'Racetrack' Memory Could Replace Hard Drives?

Galactic_grub writes "An experimental new type of memory that uses nanosecond pulses of electric current to push magnetic regions along a wire could dramatically boost the capacity, speed and reliability of storage devices. Magnetic domains are moved along a wire by pulses of polarized current, and their location is read by fixed sensors arranged along the wire. Previous experiments have been disappointing, but now researchers have found that super-fast pulses of electricity prevent the domains from being obstructed by imperfections in the crystal."

Sounds like...

[by Anonymous Coward]

...they've updated coil memory.

Re:

[AltGrendel (175092)]

I think you mean core memory [wikipedia.org].

No, core memory...

[msauve (701917)]

stores 1 bit per "core." The article is about a form of memory which continually cycles multiple bits stored as magnetic regions through a single physical ring. The OP is correct in that this is similar to cycling photons through an optical ring.

Looking back, this is all very similar to shift register memory, one of the earliest forms of solid state memory.

Re:Sounds like...

[Hal_Porter (817932)]

Actually, it's more like Bubble Memory
http://en.wikipedia.org/wiki/Bubble_memory [wikipedia.org]

Re:

[vadim_t (324782)]

It sounds more like Delay line memory [wikipedia.org] to me.

Re:

[Intron (870560)]

Bubble memory was like delay-line memory, but retained the data when the power was off. Not clear from the article whether racetrack can be non-volatile, but it needs that to compete with disk.

Re:

[morie (227571)]

I think you mean "Audio like..."

What a nice game, this "guess what he means". I wonder how many more replies there (their/they're/there're) will be.

Delay line memory

[NotQuiteReal (608241)]

It reminded me of Delay Line Memory [wikipedia.org]

I remember tearing apart a small one as a kid - out of a 100 lb 80 x 25 monochrome CRT. A bunch of wire in a foot square metal box.

I've seen it in fibre before...

[simm1701 (835424)]

I remember reading some research a couple of years ago that somethign similar was done using 100km of optical fibre and a router programmed to keep sending the same stuff around the loop, or it could read it/write it as it came around.

In some ways being slower is definitely an advantage, even with 100km at 10Gb/s you don't have much storage when the bits are moving at the speed of light.

Re:I've seen it in fibre before...

[kaszeta (322161)]

I remember reading some research a couple of years ago that somethign similar was done using 100km of optical fibre and a router programmed to keep sending the same stuff around the loop, or it could read it/write it as it came around.

The basic technique is even older than that. Google "Mercury Delay Line" for early examples: they'd make a long thin tube of mercury with transponders at each ender. It was around 5 ft per K, IIRC.

Re:I've seen it in fibre before...

[by Anonymous Coward]

Mercury delay lines were the cause of a bizarre
computer architecture. The normal form of instructions
had an "address of next instruction" field.

After getting the program to "work", i.e get the correct
answer, the "optimization" stage consisted of working out how
long each instruction would take, and then positioning the "logically next"
instruction at the location just about to appear out of the delay line.

There was no advantage to inner loops that were faster than the
delay round the mercury loop. Unless you could unroll and fit two
repetitions into one trip round.

Of course, all of this was done by hand.

Plus one addressing

[A nonymous Coward (7548)]

Generally known as n + 1 addressing, where n was how many operands had addresses in the instruction. Also used with drum memory, which was in the physical shape of a cylinder ion the one drum machine I used, but was mainly a head per track disk, so no seeking required. Some drums had multiple heads per track for some tracks to reduce latency further.

The optimization was great fun, my favorite part. You could make programs scream if you paid attention.

Re:Plus one addressing

[Rorschach1 (174480)]

Mel [pbm.com]? Is that you?

Re:

[A nonymous Coward (7548)]

I wish! I understand Mel *exactly*. Squeezing the last bit of performance and efficiency is heaven. It is an almost useless skill nowadays, and I don't do it any more on that level, but I sure wish ....

Re:

[Rorschach1 (174480)]

I understand completely. My thing is 8-bit MCUs, and there's nothing like the satisfaction of coming up with some elegant, tight construct where not a byte or cycle is wasted. And there's a real economic incentive for that sort of optimization, too - I'm running my code on chips that cost $1.68 each, and doing things that my competitors might use a $6 ARM chip or $20 Java module for.

Re:

[by Anonymous Coward]

if I had a dollar for every time they've said "this new XYZ technology could replace hard drives," I could buy a lot of hard drives

Re:

[simm1701 (835424)]

Sounds like an idea for a slashdot poll:

Which is your favorite vapourware "hard disk replacement"? :)

Re:

[Ant P. (974313)]

Straight from google's built-in calculator:
10 Gbps / c * 100 km = 437.209131 kilobytes

Re:

[simm1701 (835424)]

Not really...

10Gbps = 1.25GB/s
c = 300,000Km/s (2sf)

Does 100km in 1/3s

1.25GB/s * 1/3 s = 0.416GB

I think your answer is off by a factor of 1000 (or maybe 1024) :)

Informative?

[2008 (900939)]

"c = 300,000Km/s (2sf)

Does 100km in 1/3s"

Nope, 100km takes 1/3 of a millisecond or 3x10^-4 seconds

This sounds....

[Dogtanian (588974)]

...vaguely reminiscent of "Bubble Memory" 25 years ago. And everyone was saying *that* was going to replace hard drives too.

Re:

[MakerPharoah (1102947)]

Yes, reminds me of both bubble and "Twistor" type memories from the 70s (yes this is an actual thing).

Bubble memory...

[PHAEDRU5 (213667)]

I had *exactly* the same reaction.

Geez. Every 30 years, or so, everything old is new again. I'm getting tired of this constant repetition in life.

I mean, I was praying *never* to see bell-bottoms ever again, as long as I lived. Shudder.

Ah, memories...

[PHAEDRU5 (213667)]

When I was working on the development of DEC's DHU-11 at their Acre Rd., Reading, UK plant, we had this real comedian on staff.

One day, when the first protoype of the DHU-11 (we're talking wire-wrap here) was to be demoed, he rigged up a little plastic pipe that ran from the backplane of the PDP 11/24 holding the prototype to a place just out of sight of the various higher-up mucky-mucks who were receiving the demo.

Right after the machine was fired up, he took a big drag on his cigarette and blew into the p

Anything

[eldavojohn (898314)]

Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

Re:Anything

[Silver Sloth (770927)]

Anything would be better than the current way my hard drive works

You mean a technology that is

• cheap
• reliable - OK, hard drive errors do exist but I wish my car, for example, was as reliable
• standardized - OK, there are a number of standards but not that many

Yes, in the long term I don't see the hard drive as the best method of data storage but the altenatives have a long way to go before they replace it.

Hard disks vs Cars

[giafly (926567)]

ok hard drive errors do exist but I wish my car, for example, was as reliable

If I drove a car that was as as unreliable as my hard drives, I'd be dead. Three crashes in the last 4 years, all contents lost.

Re:

[ivan256 (17499)]

Something tells me that you have either heat, vibration, or power issues.

Either that or you're incredibly unlucky.

Re:

[b0s0z0ku (752509)]

Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

Hey, it works and is for the most part reliable. BTW- why does everyone assume that there won't be a need or desire for mechanical systems in the next century? Mechanical engineering and design is far from passe, and will find applications in new fields like space travel in the future.

-b.

Re:Anything

[pla (258480)]

Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

I know you meant that as a joke, but...

You should take a HDD apart some time. Though manufactured to incredibly small tolerances, they only really have two moving parts - the platters, and the head assembly (which despite having a lot of sub-parts, moves as a single unit).

And aside from them, you don't even have that much else that goes into a HDD - usually two air filters (one for keeping internal air clean, and one that balances external air pressure changes); the body itself (just a big aluminum block with an airtight lid); A magnet assembly for moving the heads; and the electronics on the visible external board. Sometimes you have one more small mechanical bit that doesn't seem to do anything (perhaps it parks the heads for shipping?); And that about covers it.

Re:

[dotfile (536191)]

That extra little mechanical bit is a head lock - keeps them from flopping around while the drive's powered down.

Re:

[Dogtanian (588974)]

That reminds me of something I'd almost forgotten; the first Amstrad PC clones (*) that my Dad had at work required you to run a utility to "manually" park the heads on the hard drive before you powered down. Or maybe I'm remembering it wrong.

(*) Amstrad is a British company who (amongst other things) sold the first *really* successful PC clones on the UK market.

Re:

[dargaud (518470)]

I understand the need for air to keep the head flying off the surface of the platter. What I don't understand is the need to have a hole to exchange the air with the outside. Can't they just fill it with neutral gas at the optimum pressure and seal the damn thing ? I say that because I've used hard drive at high altitude and they FAIL often. I mean, if they can do it with salad, why can't they do it to HDs ?

Re:Anything

[Nimey (114278)]

They're not sealed because air pressure is a powerful thing. If you take a laptop with a sealed hd on an airplane, the pressure changes in flight could throw various parts out of true. There'd also be metal fatigue just from normal air-pressure changes due to weather.

In other words, the guys who've been designing hard drives for the past few decades aren't stupid.

Re:

[suggsjc (726146)]

they only really have two moving parts

I'm not saying that flash memory is the answer, but it has zero moving parts.
The last time I checked two is an infinitely larger number than zero.

So I'm not knocking HDDs as the R&D, and precision engineering involved is noting to scoff at, but I think we can all agree that it isn't the ideal medium for storage.

Re:Anything

[tlhIngan (30335)]

Flash memory is no good because it has a limited number of write cycles (typically about 10,000 - after which it becomes 'random'. If a swap file was on flash memory, it'd soon die..)

Very low-end flash memory has that kind of write cycles. And it's typically limited to NOR flash, which is used only for code memory and limited data store due it its large cell size (largest NOR flash chips are around 256MB). Even so, Intel's StrataFlash had write lifetimes of at least 100,000 erase-write cycles, and most flash chips are underrated by an order of magnitude.

Modern bulk-dsta storage flash is NAND flash, which due to its smaller cell size (partly due to its design, and partly due to operation), means 16GB (byte, not bits) per chip is starting to become practical. NAND flash is faster erasing and writing than NOR flash, but much slower (order of magnitude) slower at reading. Plus it's I/O based - you can't "boot" from NAND flash like you can from NOR. (Write/Erase/Reads are on the order of microseconds for NAND - typically 100-500uS for write/erase, and 10uS for reads. For NOR, writes are typically 300-1000milliseconds, erases 1000ms, but reads on the order of 100ns or less).

Because of the operational characteristics of NAND flash, it typically has a 100,000 write-erase cycle limit at the minimum, with most offering at least 1,000,000 cycles (and typically lasts an order of magnitude more).

Wear-levelling algorithms and bad-block handling increase the time between writes and erases to the point where it almost isn't a consideration anymore - when the drive dies eventually, it'll really be timeto change it. And at least when an SSD dies, it dies on erases and writes, and very rarely on read. So if you get write errors, you still have a great probability of recovering all the data (except the data which was just written).

It's write-erase cycles, because erasing turns "0" bits into "1" bits. Writing turns "1" bits into "0" bits. Within certain restrictions, you can do multiple writes to a block (turning "1" bits into "0" bits, but you can't turn a "0" bit into a "1" bit without erasing), but those don't count towards write-erase cycles. (This behavior is often exploited when marking blocks as dirty and such). And they only fail on writes or erases due to internal timeouts (each cell takes progressively longer and longer to erase and write). Reads can be considered as never failing.

Re:

[drooling-dog (189103)]

A thousand moving parts?! What is this, the Stone Age?!

Yes, but when they fail you have some cool magnets to play with!

Goddamn kids

[PixelScuba (686633)]

Bah, in my day, the REAL Stone Age, we had to etch hash marks into a nearby rock to save our data. You damn kids and your fancy, rewritable magnetic storage media.

Re:

[comradeeroid (1048432)]

Anything would be better than the current way my hard drive works. Spinning discs on a platter?! A thousand moving parts?! What is this, the Stone Age?!

Well, actually it's worse than the stone age. Back then we had "Monoliths" which (apart from glacial shift and other geological "features" - or "bugs" as anyone outside sales management called them) had no moving (of movable even) parts at all.

When the storage space on a monolith wasn't enough you could expand to a "Circle".
Still, the space on a full c

Re:

[BrewedInTexas (971325)]

That was a quick trip to Godwin's.

Re:

[AlecC (512609)]

Almost as bad as the engine of my car. Lumps of metal hurling themselves up and down hundreds of times a second, accelerating and braking over and over again. Tolerances of a hair thickness running at hundreds of degrees and expecting tom be kept oiled without burning the oil. Fires meing lit ans extinguished ijn millisecond. Camshafts? Valves? Timing chains? All expected to keep in exact step? It'll never work, I tell you. And if it does, it will only run for minutes before something in the whole haywire m

Who needs nylon?

[Andy_R (114137)]

I just ping foreign servers a lot

Potential for fun

[Rob T Firefly (844560)]

How racetrack-like are we talking about? Does it smell like spilled booze and horse puckey? Can I gamble away the kids' college money on it?

Re:

[hotdiggitydawg (881316)]

Does it smell like spilled booze and horse puckey?

That's a rather zen-like question: what do the vapours of vapourware smell like if they don't exist?

Can I gamble away the kids' college money on it?

I'm sure there will be an overambitious start-up somewhere looking to leverage this, and bring in some gullible venture capitalists, so in that sense your wish may yet be granted.

there != their

[niceone (992278)]

their location.

I will stop now before I make a simple grammatical error myself.

(yes, I know you're looking, hmm, hmm, must be one here somewhere)

Everything old is new again

[overshoot (39700)]

Sweeeeeeeet! Bubble memory is back.

The more things change,

[gillbates (106458)]

The more they stay the same.

For those who don't know, delay line memories [wikipedia.org] have been around for at least 50 years...

Kind of interesting that they are using an old concept with new technologies.

Carbon nanotubes?

[f00Dave (251755)]

However, there are still problems that need to be overcome before the technique could be used more widely. In particular, small crystal imperfections in the wire impede progress, slowing down some domain walls and stopping others altogether.

Maybe it's obvious, but wouldn't carbon nanotubes be a prime suspect, here?

That's not bubble memory...

[Yoozer (1055188)]

It's Shigawire! [wikipedia.org]

This will bring us one step closer to the Dune Universe. I call dibs on the first load of Spice!

Racetrack?

[PPH (736903)]

Are we talking Gand Prix, Baja 1000 or stock car?

At least it'll make a crash a lot more fun to watch.