[gmx-users] cpu detection in 3.2.1 double precision

[David]

On Fri, 2004-08-27 at 21:55, Milton Taidi Sonoda wrote:
> Hi David
> Yes, it should be. I have gromacs 3.2.1 in double precision installed
> on Athlon MP with Linux RH 9.0 and FreeBSD 5.2.
> Although Athon does not support it, gromacs tries to
> probe SSE2.
> 
> Now, on Opteron 242 I have Fedora 2, for 64 bits,
> gromacs doesn't try to probe SSE2. At least
> there is nothing in the log file that shows this.
> 
> I've installed fftw-2.1.5 and gromacs 3.2.1 from
> source code. I've also tried single precision and
> enabling/disabling mpi, but none tried to find SSE/SSE2.
> 
> Could the 64 bits system has something to do with this?
> Maybe it has a different directory tree.
> 
I've tried it first on an Opteron with 32 bit OS and then on Athlon64
with FC2, 64 bits. Both work. Although this is with the CVS code, I'm
pretty sure nothing has changed in that bit. Have you updated to the
latest kernel on your Opteron? Mine is at:

[appel1:gmxbench/d.villin] % uname -a
Linux appel1 2.6.8-1.521 #1 Mon Aug 16 09:01:00 EDT 2004 x86_64 x86_64
x86_64 GNU/Linux


> Milton Taidi Sonoda
> 
> David wrote:
> 
> >On Thu, 2004-08-26 at 22:46, Milton Taidi Sonoda wrote:
> >  
> >
> >>Hi
> >>I'm testing gromacs 3.2.1 in a two nodes cluster
> >>of opteron 242, compiled in double precision.
> >>
> >>I've searched the log and job files
> >>for the stage where gromacs tries
> >>to detect CPU version for optimization
> >>but I didn't find it.
> >>    
> >>
> >It's in the md.log file. Look foor SSE:
> >
> >Testing x86 processor CPUID...
> >CPU manufactured by AMD.
> > 
> >Testing x86 SSE2 capabilities...
> >CPU and OS support SSE2.
> >Using Gromacs SSE2 double precision assembly innerloops.
> > 
> >
> >
> >  
> >
> >>I'm sure I didn't --disable-cpu-optimization
> >>during configuration.
> >>
> >>Is any thing wrong?
> >>
> >>Is gromacs using the SSE2 or other capabilities
> >>of opteron 242?
> >>
> >>Thank you.
> >>[ ]'s
> >>Milton Taidi Sonoda
> >>
> >>
> >>_______________________________________________
> >>gmx-users mailing list
> >>gmx-users at gromacs.org
> >>http://www.gromacs.org/mailman/listinfo/gmx-users
> >>Please don't post (un)subscribe requests to the list. Use the 
> >>www interface or send it to gmx-users-request at gromacs.org.
> >>    
> >>
> 
> 
> 
> _______________________________________________
> gmx-users mailing list
> gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
-- 
David.
________________________________________________________________________
David van der Spoel, PhD, Assoc. Prof., Molecular Biophysics group,
Dept. of Cell and Molecular Biology, Uppsala University.
Husargatan 3, Box 596,  	75124 Uppsala, Sweden
phone:	46 18 471 4205		fax: 46 18 511 755
spoel at xray.bmc.uu.se	spoel at gromacs.org   http://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++