Re: gfortran transition release goal proposal
On Tue, Jul 24, 2007 at 11:47:49AM -0400, Camm Maguire wrote:
> I suppose everyone is aware that -ffloat-store is a real performance
> loser, especially on slower machines. Would it be preferable to fix
> the testers to not be fooled by extra precision?
Yes, fixing testers would be the correct (tm) solution. Depending on
how busy you/refblas3 upstream are, you may want to start with
-ffloat-store and fix the testcases later when there is no hurry for
transition.
Reply to: