View Single Post
  #19 (permalink)  
Old 6th July, 2006, 10:03 AM
Aedan Aedan is offline
Chief Systems Administrator
Join Date: September 2001
Location: Europe
Posts: 13,075

We're already having issues with electrons being too slow...

For example, a PCB that's Polyimide based has a propagation velocity of 173mm/nS. Whilst that might sound fast, it doesn't take very much to upset the leading edge of a signal. When dealing with high speed logic (such as GDDR), the margin for error is tiny. Looking at PCI Express, the effective operating frequency of a link is 7GHz, due to the rise time (50pS). (Don't confuse this with the clock frequency of the link - they are different.)
Any views, thoughts and opinions are entirely my own. They don't necessarily represent those of my employer (BlackBerry).

Last edited by Áedán; 6th July, 2006 at 10:15 AM.
Reply With Quote