This is the mail archive of the
fortran@gcc.gnu.org
mailing list for the GNU Fortran project.
where is math function inlining decision done?
- From: IainS <developer at sandoe-acoustics dot co dot uk>
- To: Fortran List <fortran at gcc dot gnu dot org>
- Date: Fri, 20 Jun 2008 13:00:01 +0100
- Subject: where is math function inlining decision done?
I decided to examine one of the outliers in the benchmarks.
It seems that although the output of
-fdump-tree-optimised
is quite similar.
however, process sampling indicates that fmod might be the culprit ....
In the case of one processor __builtin_fmod is getting replaced by an
inline
In the case of the other __builtin_fmod is generating a call to libm.
Where does gcc decide how to replace __builtin_fmod ?
thanks,
Iain