On Sun, Apr 14, 2013 at 03:03:12PM -0700, David Barbour wrote:

> And I've seen Grace Hopper's video on nanoseconds before. If you carry a
> piece of wire of the right length, it isn't difficult to say where light
> carrying information will be after a few nanoseconds. :D

Few ns are effective eternities in terms of modern gate delays.
I presume the conversation was about synchronization, which 
should be avoided in general unless absolutely necessary, and
not done directly in hardware.

Ditto clocks, as distributed systems of oscillators would
tend to sync up due to local coupling. No need for a centralized,
global clock. Purely asynchronous CPUs show clocks are not necessary,
and even for cloked systems there are ways to save on power
and distribution delays 

http://spectrum.ieee.org/semiconductors/processors/powersaving-clock-scheme-in-new-pcs

http://www.extremetech.com/computing/119507-amd-to-use-resonant-clock-mesh-to-push-trinity-above-4ghz
_______________________________________________
fonc mailing list
[email protected]
http://vpri.org/mailman/listinfo/fonc

Reply via email to