VMD-L Mailing List

From: John Stone (johns_at_ks.uiuc.edu)
Date: Fri Sep 01 2017 - 14:34:31 CDT

Axel,
  I'll have a look at your plugin and see what I can learn from it.
The internal VMD components for things like parallel work scheduling
are in some respects relatively seperable from the low-level message
passing, except that VMD wants to pass in MPI_THREAD_SERIALIZED
to MPI_Init, and it wants to do some low-level thread stuff
for the parallel work scheduler, but I'll see if there's an opportunity
to converge ideas in your implementation with what's in VMD.

The MPI implementation in VMD hasn't really changed very much since 2010.
I had been hoping that the MPI committee would finally get an ABI
approved and/or that projects like MorphMPI would take off and make
all of this a non-issue, but we're still not quite there yet.
Unless something new is on the near-term horizon, doing a plugin
like you've done or like I described may still be the practical
way to make this more broadly available.

Best,
  John

On Fri, Sep 01, 2017 at 03:10:44PM -0400, Axel Kohlmeyer wrote:
> On Fri, Sep 1, 2017 at 2:12 PM, John Stone <johns_at_ks.uiuc.edu> wrote
>
> >
> > The reason that the standard VMD builds don't include MPI by default
> > is because MPI lacks a binary runtime interface, and requires that
> > applications be compiled from source code on the actual target
> > hardware where they will be run. To make the deployment of VMD
> > with MPI easier, I have been considering making the MPI aspects of
> > VMD operate using a plugin type interface and shipping the MPI-related
> > plugin source code along with VMD so that an existing VMD binary for
> > Linux/Windows/MacOS could just load such an MPI plugin at runtime,
> > and you wouldn't have to recompile the whole program, which as many
> > here already know is quite a task, particularly for beginners.
> >
>
> FWIW: there is already an external MPI plugin for Tcl, that can be used to
> parallelize VMD using fast message passing networks via MPI.
> https://sites.google.com/site/akohlmey/software/tclmpi
>
> this exists for over 5 years and i have been using it very successfully
> to parallelize plain Tcl scripts but also VMD/Tcl script (e.g. where each
> VMD instance loads a subset of a trajectory). you compile the plugin
> separately, test it with your local Tcl installation and the load it into
> VMD without having to recompile VMD.
>
> the main limitation of this plugin is, that it is made for generic Tcl and
> thus only supports Tcl data structures (thus it cannot communicate VMD
> internal data directly). on the other hand, it is completely independent of
> VMD and can be used with any compatible Tcl interpreter.
>
> axel.
>
>
> > Best regards,
> > John Stone
> > vmd_at_ks.uiuc.edu
> >
> > On Fri, Sep 01, 2017 at 01:34:59PM +0200, Ajasja Ljubeti?? wrote:
> > > Hi!
> > > You're not giving a whole lot of details, so my advice will be
> > generic as
> > > well. Usually I split my trajectories into 1 ns chunks and then I use
> > > [1]gnu parallel?? to run analysis scripts in parallel.??
> > > If you mean the parallel [2]tcl command?? you have to compile VMD with
> > MPI
> > > support and have MPI installed. But I guess this is meant for large
> > > clusters of computers not just a four core processor (or two, in case
> > of
> > > hyper-threading).
> > > Best,
> > > Ajasja
> > > On 1 September 2017 at 12:59, Saikat Pal
> > > <[3]saikatpaliitg_at_remove_yahoo.com> wrote:
> > >
> > > Dear all,
> > > I want o install VMD IN parallel to analysis data.What should I do
> > ??I
> > > have already installed VMD in serial mode .In my computer there are
> > 4
> > > processors are available.Please help me out .
> > > Thanks And Regards,
> > > Saikat
> > >
> > > References
> > >
> > > Visible links
> > > 1. https://www.gnu.org/software/parallel/
> > > 2. http://www.ks.uiuc.edu/Research/vmd/current/ug/node144.html
> > > 3. mailto:saikatpaliitg_at_remove_yahoo.com
> >
> > --
> > NIH Center for Macromolecular Modeling and Bioinformatics
> > Beckman Institute for Advanced Science and Technology
> > University of Illinois, 405 N. Mathews Ave, Urbana, IL 61801
> > http://www.ks.uiuc.edu/~johns/ Phone: 217-244-3349
> > http://www.ks.uiuc.edu/Research/vmd/
> >
> >
>
>
> --
> Dr. Axel Kohlmeyer akohlmey_at_gmail.com http://goo.gl/1wk0
> College of Science & Technology, Temple University, Philadelphia PA, USA
> International Centre for Theoretical Physics, Trieste. Italy. 

-- 
NIH Center for Macromolecular Modeling and Bioinformatics
Beckman Institute for Advanced Science and Technology
University of Illinois, 405 N. Mathews Ave, Urbana, IL 61801
http://www.ks.uiuc.edu/~johns/           Phone: 217-244-3349
http://www.ks.uiuc.edu/Research/vmd/