The new scheduler and x86 CPUs

[Bernd Schmidt]

On Tue, 28 Aug 2001 dewar@gnat.com wrote:

> <<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.

There are several cases where less extensive analysis is needed at run-time
(e.g. to determine memory aliases), or where certain aspects of the program
are only available at run-time, since they are variable (e.g. load
latencies).

> Now of course the question of whether EPIC architectures
> + clever compilers can in *fact* do better than OOO cores remains to be seen.

Don't forget that if your compiler can do something very clever, it can do
so for both EPIC and OOO>


Bernd