I see. Thank you for the detailed response. It sounds to me that GPUs could be a better option if there was significantly more stability and standardization across the board, but we're really just not in that place.
The memory barrier may still be there but my guy feeling is we would have so much more code running on GPU then that there would have been solutions developed for this, too, long ago.
Raph Linus is currently writing a blog post from the perspective of someone who has been working on GPU-accelerated 2D vector rendering.
It echos some of the issues I touched on above.
Well worth reading when it is released (probably will hit HN front page anyway):