[gmx-users] 3.1 with mpi on an IBM SP

[David L. Bostick]

Oops! 

Yes it does..  Sorry for cluttering the users list with questions I can
answer myself..

Thanks,
David

-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
David Bostick					Office: 262 Venable Hall
Dept. of Physics and Astronomy			Phone:  (919)962-0165 
Program in Molecular and Cellular Biophysics 
UNC-Chapel Hill					
CB #3255 Phillips Hall				dbostick at physics.unc.edu	
Chapel Hill, NC 27599	           		http://www.unc.edu/~dbostick	
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

On Thu, 7 Mar 2002, David L. Bostick wrote:

> 
> Hi,
> 
> I have a simple question.  I have fftw libraries installed on an IBM SP for
> both scalar and mpi.  They are compiled in both single and double precision
> and have the corresponding type prefixes s for single and d for double.
> The mpi compiled versions have the suffix, "_mpi" on them.  All of these
> libraries are in the fftw/include and fftw/lib directories as usual.
> However, it seems that the configure script only checks for the s or d type
> prefix.  Is there a way to specify that for mpi compiling, I want the
> configure script to recognize the _mpi suffix?  Does it do this already?
> 
> Thanks,
> David
> 
> 
> -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
> David Bostick					Office: 262 Venable Hall
> Dept. of Physics and Astronomy			Phone:  (919)962-0165 
> Program in Molecular and Cellular Biophysics 
> UNC-Chapel Hill					
> CB #3255 Phillips Hall				dbostick at physics.unc.edu	
> Chapel Hill, NC 27599	           		http://www.unc.edu/~dbostick	
> =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
> 
> _______________________________________________
> 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.
>