[MPlayer-users] Possible bug [FreeBSD 5.0-CURRENT]

[Felix Buenemann]

On Thursday 04 July 2002 09:40, Per-Arne Holtmon Akø wrote:
> On Wed, Jul 03, 2002 at 23:20:47 +0000, Felix Buenemann wrote:
> > [Automatic answer: RTFM (read DOCS, FAQ), also read DOCS/bugreports.html]
> >
> > On Wednesday 03 July 2002 21:13, Per-Arne Holtmon Akø wrote:
> > > > > > what cpu do you have and which values were used for -march,
> > > > > > -mcpu?
> > > > >
> > > > > athlon-xp for both. I have Athlon MP's.
> > > >
> > > > afaik Atnlon XP and Athlon MP (that's the SMP model if I haven't
> > > > mixed it up), are pretty much the same core, so I guess you are right
> > > > and it's a compiler bug. You could use gdb + disass to trace the
> > > > faulty instruction...
> > >
> > > If someone would mind holding my hand through the process I'm more than
> > > willing to try this.
> >
> > DOCS/bugreports.html is your friend.
>
> Ok, I did what was said to do for a reproducible crash, and I've
> attached the output from the whole gdb session.
OK, I tracked down the problem.
Athlon XP/MP and some other Athlon models all share the same CPUID (666), but 
only the XP supports SSE, this leads to miscompiled code for MP and others.
Your log also shows, that gcc uses SSE which is not possible on your cpu.

I have now commited a fix to configure, that will fallback to athlon-4 
optimization, if no SSE is detected.

However if you want to get the most out of your cpu, you should edit the 
config.mak to use -march=athlon-mp -mcpu=athlon-mp, as the MP is not 
currently auto-detected as MP but as Athlon-4.

Please test if current configure fixes your prob and report back.

And if you have linux /proc/cpuinfo emulation, it would be nice, if you could 
paste the output here.
-- 
Best Regards,
        Atmos
____________________________________________
- MPlayer Developer - http://mplayerhq.hu/ -
____________________________________________