The new scheduler and x86 CPUs

dewar@gnat.com dewar@gnat.com
Tue Aug 28 15:20:00 GMT 2001


<<Why is OOO a dead-end approach?  If there's parallelism to extract
in a program, then if a compiler can find it, an OOO core can find it
just as well.
>>

That's clearly false, since the OOO core has to do things on the fly in
very limited time, while a compiler can do extensive analysis without
such time constraints. Now of course the question of whether EPIC architectures
+ clever compilers can in *fact* do better than OOO cores remains to be seen.
It is fascinating that the competition between Intel and AMD moves away
from who can build a better ia32 to a competition between two radically
different architectural approaches.



More information about the Gcc mailing list