But how's it fold?

[Sorin]

IBM breakthrough, one step closer to optical computers

Yorktown Heights (NY) - IBM announced today reaching a significant milestone in practical on-chip optical data transmissions. Using a device called a Mach-Zehnder electro-optic modulator (MZEOM), one that's 100 to 1,000 times smaller than similar previous devices, IBM has managed to send 100x more data between processor cores using 10x less power than over copper wires. IBM plans to integrate this technology into their future many-core architectures, eventually bringing our desire for 1000s of processing cores and true supercomputing power, to even our notebooks. more... (http://www.tgdaily.com/content/view/35171/118/)

Another link, with video (http://gigaom.com/2007/12/06/ibm-optical-breakthrough-can-put-supercomputer-on-a-chip/)
Another link (http://www.freerepublic.com/focus/f-chat/1935788/posts)


Yeah yeah yeah, blah blah blah. How's it fold? :D

[harlam357]

Let's just hope we can get one with an x86 instruction set. :)

[Sleepy_Steve]

We all know it goes to big iron systems first :beer:

[Zerix01]

Will AMD get a license for the technology?

[Sorin]

Don't IBM and AMD work closely together anyways, sharing technologies? I was reading several of the comments in the TomsHardware version of the story that says they do.

Either way, I hope someone does. AMD, Intel, both. If both got it, and IBM obviously got money for the licensing or whatever, then no one gets left in the cold. :D

I think...

Economics was never my strong point.

[Zerix01]

Don't IBM and AMD work closely together anyways, sharing technologies?

Yes they have for a while. Pretty much AMD would not be where it is today without IBM. I'm including the good and the bad parts of where AMD is today.... I guess AMD is over dependent on IBM in some ways. But IBM is an R&D power house, so I have confidence the two companies will pull the current and future technologies together and start pumping out some good chips.

[AlabamaCajun]

Let's just hope we can get one with an x86 instruction set. :)

All you need is the compiler and a build switch. X86 is too slow for RISC processors.

[harlam357]

All you need is the compiler and a build switch. X86 is too slow for RISC processors.

Yeah... I'm sure that's all it would take. :rolleyes:

Actually, since Stanford already has code for PowerPC they may be able to adapt it to something like this... maybe with just a compiler switch. ;)

[Sleepy_Steve]

Oh not another client...