Re: Large slowdown with gfortran vs f77 (x7)

[Jerry DeLisle <jvdelisle at verizon dot net>]

Tobias Burnus wrote:
> On 09/04/2009 05:04 PM, FX wrote:
> >   -- it's unarguably a glibc issue: if exp() is fast and expf() is
> > slow, why doesn't glibc implement expf() by calling exp()? (yes, there
> > can be other issues like rounding or so, but they can also be dealt
> > with separately)
>
> If I recall correctly, it is mostly an x86-64 problem. AMD has some math
> patches for GLIBC which speed things up a lot. I think those are used in
> openSUSE/SLES but not in Fedora. On the other hand, the AMD patches have
> a problem with signaling NaN, which is being fixed [1,4].
>
> Some older timings (from PR 34128) on openSUSE (!)  -- for "sin" but
> there is the same problem as for exp:
>
>               g77     gfortran
> -m32  real(4) 0.408s  0.421s
> -m64  real(4) 1.040s  0.589s ! sinf on x86-64: 40% faster!
> -m32  real(8) 0.411s  0.408s
> -m64  real(8) 0.976s  0.968s ! sin on x86-64

When I dug into the library routines originally on this I discovered the slow 
routines were using a software implementation where as the faster functions were 
using the math coprocessor. It is the glibc code.

Regards,

Jerry