Do you really mean compile time? If so, issue make -j X (where x is
the number of jobs used for building).
If you mean runtime then the easiest thing is to split your trajectory
in parts and run the processes in parallel, then patch the results
together. That's if the calculations can be done on a per-frame basis
(i.e. embarrassingly parallelizable problems). Next in line is to wrap
some performance critical loop(s) in OpenMP pragmas and link to the
OpenMP libraries on your system. If you want others to benefit from
the code you should adhere to the parallelization framework in
gromacs, e.g. use gromacs' wrappers and preprocessor directives for
OpenMP and MPI magic. The latter may be more trouble than it's worth
if your analysis is only for a limited userbase. There is a framework
underway in gromacs for parallel analysis tools, but as far as I know
it's not finalized yet.
Erik
On Mar 14, 2013, at 2:22 PM, subhadipdas wrote:
First, here my system :
Cent Os 64 bits
gcc : 4.4.6
fftw : 3.3.2 including SSE 2
I am writing a code to find out the number of five and six membered
rings in
structure I of hydrate . My code takes long time to compile for my
500ps
trajectory . So my query is that can the template file be made to
run in
parallel fashion ? If so ,how
--
View this message in context:
http://gromacs.5086.n6.nabble.com/template-parallelization-tp5006320.html
Sent from the GROMACS Users Forum mailing list archive at Nabble.com.
--
gmx-users mailing list gmx-users@gromacs.org
http://lists.gromacs.org/mailman/listinfo/gmx-users
* Please search the archive at http://www.gromacs.org/Support/Mailing_Lists/Search
before posting!
* Please don't post (un)subscribe requests to the list. Use the
www interface or send it to gmx-users-requ...@gromacs.org.
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
--
gmx-users mailing list gmx-users@gromacs.org
http://lists.gromacs.org/mailman/listinfo/gmx-users
* Please search the archive at
http://www.gromacs.org/Support/Mailing_Lists/Search before posting!
* Please don't post (un)subscribe requests to the list. Use the
www interface or send it to gmx-users-requ...@gromacs.org.
* Can't post? Read http://www.gromacs.org/Support/Mailing_Lists
