Optimizing hypot()
Kaveh R. Ghazi
ghazi@caip.rutgers.edu
Thu Jul 24 11:08:00 GMT 2003
> I think hypot2 could be improved much, if it is recognized as builtin
> and optimized for sse/sse2. Is someone working on such
> transformations?
> Thanks,
> Richard.
Roger Sayle has done a lot of work recently on builtin math functions,
perhaps we can impose on him a bit more to do this too.
IMHO hypot, cbrt and perhaps ldexp are ripe for picking next.
--Kaveh
--
Kaveh R. Ghazi ghazi@caip.rutgers.edu
More information about the Gcc
mailing list