[Eug-lug] Re: Concurrency
Allen Brown
allen_brown at agilent.com
Tue Jan 11 10:14:39 PST 2005
walter fry wrote:
> At last something I can understand,,In the late 1960's I heard a comment
> that the next great breakthrough would be three dimensional chip
> architecture, at that time it was thought that heat dissipation would
> become the biggest hurdle
Heat dissipation is a huge issue still.
>> What causes most of the slowdown in going from CPU to main memory is
>> the pads and PC board. On chip signals have orders of magnitude less
>> capacitance and so can go at least an order of magnitude faster.
>>
>> One technology that is being considered is optical interconnect. That
>> would provide a tremendous speedup to this pathway. The technology
>> isn't ready yet. I don't know how long it will take to appear.
>>
>> But once you have optical interconnect, it can be used on chip as
>> well as off chip. Recall that Herb indicated the speed limit of
>> current processors is basically caused by interconnect. Optical
>> interconnect changes that and greatly reduces the speed cost of long
>> distance signaling
>
>
> Perhaps vertical integration is waiting for optical interconnects, which
> would probably be GaAs due to higher speed than Si as well as higher
> efficiencies
> WF
Silicon has improved to the point where GaAs's speed advantage is
not so high.
I think vertical integration is constrained by power. The
exception is RAM, which potentially doesn't need as much.
A way to eliminate the power problem would be to switch to
a carbon substrate. Diamond is an excellent thermal conductor.
And the resulting transistors can run at much higher temperatures
without melting.
--
Allen Brown
work: Agilent Technologies non-work: http://www.peak.org/~abrown/
allen_brown at agilent.com abrown at peak.org
I think I think; therefore, I think I am. ---Ambrose Bierce
More information about the EUGLUG
mailing list