Same author did the synthesis kernel with Carl Pu, I think? The Synthesis kernel was genius, but relied on self modifying code, so can't work with modern chips well.
yes. Calton Pu. is that really such a problem? JITs seem to work pretty well, I'm pretty sure synthesis was more about creating custom paths than being strictly self-modifying, but its been a long time.
Same author did the synthesis kernel with Carl Pu, I think? The Synthesis kernel was genius, but relied on self modifying code, so can't work with modern chips well.
yes. Calton Pu. is that really such a problem? JITs seem to work pretty well, I'm pretty sure synthesis was more about creating custom paths than being strictly self-modifying, but its been a long time.
I love love love this paper. I wonder how a GPU would do with it?
(1987)