Israeli Processor Computes at Speed of Light

[amigamad]

who needs ppc with this kind of speed. :-)

[AmigaHeretic]

If it had an accelerator card based on a CPU like this in it I might actually change my mind about the A2000 really being a Professional Computer!   :-D

[SilvrDrgn]

Gee, this processor might (<- key word there) have a possibility of making Win-DOHS run at a respectable speed!    :-P

[Oldsmobile_Mike]

I'll take a thousand.  Need something to run my Beowulf cluster on.   :-o  :-D

[thorrin]

Nice, but the only downside is that you can't build a processer faster than this because what is faster than light?

Why would we need one faster than this?  After all, 640K should have been enough memory right?  Who would ever need that much memory? :-D

I guess you just run a bunch of these in parallel to get faster.

-Thorrin

[sTix]

hmm, this might be a silly question but what
is "the speed of electricity" then?

[AmigaHeretic]

@sTix

I believe if electricty is moving through a medium that has no resistance (a super-conductor) then it travels at or near the speed of light.  Of course most wire isn't super-conudcting so it moves a little slower than that.  I could be wrong though  :-)

[AmigaHeretic]

Nice, but the only downside is that you can't build a processer faster than this because what is faster than light?

There are particles believed to exist called FTL particles (Fast Than Light).  One of the more common particles believed to exist are called Tachyons. ( of course there are many that believe they don't exist as well).

Of course there's still that question of turning you're headlights on while going down the highway at 70mph (yeah I'm in the US  :-)  )  Does that mean the light is traveling at 70 miles faster than the speed of light?  Einstein seems to think not.

[IonDeluxe]

I think the phrase" processing at the speed of light" is somewhat misleading.
The question is not how fast light or electrons move, but rather how fast the flow reached a stable lvl when the contacts of a switch meet(be this mechanical or inside a processor)
thats what resistance is, and expression of forces working against the flow of electrons.
IF you could produce a CPU that had zero resistance, there would be no restriction of the flow of the elctrons and the amount of processing power would be theoretcly unlimited.Also this would produce no heat as heat is a by product of resistance.
The problem with light is changes to its flow are not instantaneous, and this is why hardline calls on a phone are actually much faster than using satellite communications across the globe.
All that being said it looks promising, even if they really dont describe how it works.
I wonder how this will compare to the Quantum processors being developed by IBM and other sundry organizeations.

[Damion]

I think the phrase" processing at the speed of light" is somewhat misleading.
The question is not how fast light or electrons move, but rather how fast the flow reached a stable lvl when the contacts of a switch meet(be this mechanical or inside a processor)
thats what resistance is, and expression of forces working against the flow of electrons.

I agree. And according to the flimsy details
provided by Reuters, it's not really a complete
processor, but a device which works in tandem
with a 'normal' DSP.

IF you could produce a CPU that had zero resistance, there would be no restriction of the flow of the elctrons and the amount of processing power would be theoretcly unlimited.Also this would produce no heat as heat is a by product of resistance.

Becasue of this I think the real future will
eventually lie with metallic hydrogen, if
scientists ever figure out a method to
stabilize it in such a state. They *have*
been able to control it long enough to measure
its resistivity...and the although the results
haven't been quite as spectacular as anticipated,
the potential for future applications (which
require near perfect conductance) is promising.

[iamaboringperson]

optics instead of silicon, enabling it to compute at the speed of light..."

Using photons instead of electrons doesn't mean that it will necessarily compute faster however...

[iamaboringperson]

"Optical processing is a strategic competitive advantage for nations and companies," said Avner Halperin, vice president for business development at Lenslet.

"Processing at the speed of light, you can have safer airports, autonomous military systems, high-definition multimedia broadcast systems and advanced next-generation communications systems."

Nice propaganda ... what else can it do?

[Floid]

Try here:

http://lenslet.com/technology.asp

Nice.  As far as I can tell, it's an advantage in parallelization more than an advantage explicitly tied to optical frequencies... it just happens that it's a lot easier to parallelize with optics than in transistors?

Now call me stupid... I've looked at it back and forth three ways, and this *is* analog computation, isn't it?  The 'result' is directly level-dependent and gets pulled through an ADC?  So what we have here is one of the world's coolest digitally-programmable analog computers?

(Hint: There are 'slightly less than as-close-to-purely-digital-as-we-can-get' technologies in action everywhere; Intel's StrataFlash is a good example.)

But it does seem like they'll want some noise reduction (use of digital-style quanta, AKA 'bits') if they want to *really* guarantee the results... while at the same time, the properties of the light mean they do get a StrataFlash-grade guarantee.  (You know how much light is coming through each cell, which is presumably a Much Larger Number than the noise floor of the detectors.)  Reworking it to approach digital perfection would probably kill their speed advantage, but at the same time... isn't there some way we could do the same "para-analog" manipulation in silicon?

...which in turn is the sort of trick Sun was/is looking to implement in their attempt at asynchronous architecture?  ('Instructions' get implemented by magic blocks of circuitry... oof, now I need to dig up the name for that project.)

[Floid]

Sun links:

http://research.sun.com/async/
http://research.sun.com/async/Publications/KeyPapersPD1.html