[gmx-users] XT3 porting

[Tom Joseph]

Providing a backtrace or two would really help.  Given the exact same  
input files and run conditions, does it sometimes segfault and  
sometimes not? Does this happen on a login node (full glibc and such)  
or just the compute nodes (POSIX subset)?

Separately, is it a better idea to use fftw2 since it supports MPI?

(Hopefully soon my Teragrid access will extend to bigben, so I'm  
especially interested in this...)

--Tom

On Apr 17, 2006, at 10:06 PM, Shawn T. Brown wrote:

> Hello, I am trying to port GROMACS 3.3.1 to the CRAY XT3, which is  
> essentially an Opteron machine with the PGI compilers.  I can get  
> everything to compile, but when I run mdrun, I am “randomly”  
> getting segmentation faults.  This seems to happen no matter what  
> input file I use.  It happens in init_forcerec (line 1001), in  
> add_gbond, and in solvent_check.  Some times it runs fine.  I am  
> configuring with the following command:
>
>
>
> ./configure --with-fft=fftw3 --disable-nice --enable-mpi --program- 
> suffix="_xt3" --enable-float --with-external-blas --with-external- 
> lapack --disable-threads --prefix=/usr/local/packages/gromacs-3.3.1
>
>
>
> I am wondering if anyone else has seen these types of problems and  
> knows how to fix them.  I have tried compiling the code without  
> optimization, to no avail.
>
>
>
> Thanks in advance,
>
> Shawn
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-users/attachments/20060417/b9ce57a5/attachment.html>