pb with -ffast-math

[Alain Baeckeroot]

Le 15/04/2009 à 19:56, Jaroslav Hajek  écrit :
> 
> On Tue, Apr 14, 2009 at 9:54 AM, Alain Baeckeroot
> <alain.baeckeroot at laposte.net> wrote:
> >
> > i builded octave with additional optimisation flags
.../...
> 
> I use -O3 -march=native -funroll-loops and get good results.
I'll try this.

> 
> > And this is really not important, i doubt we can get another 20%
> > speed improvement.
>
> Depending on your code, you may get even much better improvements by
> switching to the development sources (it seems you use 3.0.5). An
> instance is the experience of F. Potorti:
> http://www.nabble.com/thanks-for-the-indexing-improvements-td22494818.html#a22494818
> 
Everythnig is vectorised, except one for-loop (iteration over time) which
 takes 90% of time !
We are going to write this short part in C in a .oct file.

I'll try latest develpment source to see what happens.

Thanks
Alain