Re: Bug#212912: gcc-3.3: [alpha] Linux linker/loader does not support -mieee-conformant
Matthias Klose <doko@cs.tu-berlin.de> writes:
> As Chris (currently listed as package maintainer for gcc alpha)
> seems to be away, I'll ask on debian-alpha (Falk?), if this patch
> should be included.
I'd vote for not including it like it is now.
> > Richard Henderson (the Alpha fellow from Red Hat) said he wouldn't
> > accept it into the general GCC unless all users of GCC (i.e. BSD,
> > etc) came forward and said they wanted it.
> >
> > He also gave three reasons why he personally didn't like it:
> > 1- The default under DEC C is to not IEEE compliance
> > 2- IEEE compliance leads to 'severe' performance penalties
> > 3- The vast majority of SIGFPEs are due to unitialized data reads
> >
> > While one and three might be true (timing tests show that two is
> > just plain wrong),
Well, 20% looks pretty severe to me.
> > they miss the point of the patch.
> >
> > The patch is intended to help achieve the goal of having as many
> > packages as possible run on the Debian Alpha distribution as
> > possible (without needing to specify Alpha specific flags).
Then we should also compile with -O0 to avoid triggering bugs? There
has to be some trade-off.
> > This means matching the GNU defaults on the other Debian
> > architectures, and that just happens to be IEEE compliant
> > libraries and code.
It has also been a GNU policy to not be standards compliant just for
the sake of it. Very little code actually needs IEEE complicance.
Like rth, I'd say as a minimum -ffast-math should turn off IEEE
complicance. When that's the case, the patch would be OK with me,
since actually also very little code needs high floating point
performance.
--
Falk
Reply to: