[CP2K:453] getting rid of hard-coded MPI_COMM_WORLD

[Fawzi Mohamed]

I wrote the f77_interface trying to exactly achieve that.
There are two routines to create force_envs one that recieves  
explicitly a group (actually a communicator, in cp2k we have it  
sistematically misnomed) and another that has no arguments (and  
defaults to MPI_COMM_WORLD).
This is actually already used internally in cp2k and should work.
If it doesn't then it should definitly be fixed.
Or you want to change the init routine (wich just defines a general  
fallback in case of really bad errors)?

Fawzi
On Dec 5, 2007, at 12:57 AM, Axel wrote:

>
> hi!
>
> this is a RFC to the cp2k developers that hang out here.
> i'd like to change the code, so that cp2k can be run from
> a "supervisor" MPI program. that would mean to get rid of
> the (few!) hardcoded MPI_COMM_WORLD constants in
> message_passing.F and f77_interface.F so that one can
> launch a cp2k calculation on a group communicator (which
> of course would default to MPI_COMM_WORLD).
>
> any comments, suggestions, caveats would be highly appreciated.
>
> thanks,
>    axel.
>