This is the mail archive of the fortran@gcc.gnu.org mailing list for the GNU Fortran project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: where is math function inlining decision done?



On 20 Jun 2008, at 13:03, FX wrote:


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 ?

What are your compilation options? Do both processors use the same fp unit (ie, i387 or sse)?

-O2 -gdwarf-2


They are different architectures, I expect the answer to be different.

I am interested to see what happens if I supply an inline asm fmod - but I don't know how/where gcc picks this up from.

Iain


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]