[gmx-developers] Current status FFTW-3D

[Roland Schulz]

Hi David, Carsten and Erik,

I'd like to go ahead and start to implement the 3d FFT part.

Do you prefer or recommend a new implemantation or is adapting an existing 
implemantation as good? I think the 3d FFT from Steve Plimpton 
(http://www.sandia.gov/~sjplimp/docs/fft/README.html) which is used in LAMMPS 
could be used and is fulfilling the requirements. I wouldn't recommend to use 
the library as shared library (compile time dependences) but to simply take 
the code into the Gromacs CVS. This is also the way it was done for LAMMPS.

I quickly introduce myself: I studied Physics at the University of
Heidelberg and I'm now a UTK graduate student in the Genome Science and
Technology program and work in Prof. Jeremy C. Smith's group Center for
Molecular Biophysics at the ORNL.

Roland Schulz (and Jeremy Smith)


On Monday 06 August 2007 10:50, Carsten Kutzner wrote:
> David van der Spoel wrote:
> > Erik Lindahl wrote:
> >> Hi Roland,
> >>
> >> Wiki is pretty much up-to-date on the FFT stuff - I haven't had time
> >> for it myself (working on free energy perturbation right now) and my
> >> students seem to be busy :-)
> >>
> >> There are some auxiliary projects involving more optimized FFT
> >> routines, but the primary project is mostly an exercise in
> >> book-keeping and efficient MPI communication. Essentially, the
> >> parallel version should use pre-existing 1D FFT calls and enable full
> >> 1D/2D/3D decomposition of the entire grid (currently we only do 1D).
> >
> > The wiki is up-to-date as concerns information. Carsten Kutzner
> > expressed some interest in working on this, maybe he can comment whether
> > or not this is the case?
>
> Hi David, Roland, and Erik,
>
> yes, I expressed interest in working on the FFT parallelization,
> however, right now I have started to implement an additional pull
> option. I cannot say when exactly I would have time for the FFT - so
> please go ahead! I'm shure there are plenty of things to work on so that
> I will simply choose something else then.
>
> Thanks for asking!
>    Carsten
> _______________________________________________
> gmx-developers mailing list
> gmx-developers at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-developers
> Please don't post (un)subscribe requests to the list. Use the
> www interface or send it to gmx-developers-request at gromacs.org.