Le 2012-09-14 17:57, Timothy Normand Miller a écrit :
Some of you may remember a number of years ago, we discussed design
tradeoffs for memory and video controllers for OGD1. For video, we
ended up going with a microcoded component, while for memory, we went
with fixed-function. However, I described a programmable memory
controller, and another OGP member contributed an implementation.
Well, researchers at Rochester just published a paper on this very
idea.
http://www.ece.rochester.edu/~bojnordi/papers/isca12.pdf
Your microcode video controller was a really cool thing,
but the paper your just link is *jaw drop*
yg
_______________________________________________
Open-graphics mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-graphics
List service provided by Duskglow Consulting, LLC (www.duskglow.com)
