MPI_COMM_WORLD rank is exactly the vpid.
But keep in mind that when you MPI_COMM_SPAWN, they get a new
MPI_COMM_WORLD (with ranks that start with 0). Hence, with the advent
of dynamic processes in MPI-2, a process' rank in MPI_COMM_WORLD is no
longer unique (which is why OMPI uses more than that internally to
tell MPI processes apart).
On Nov 30, 2007, at 4:41 PM, Sajjad Tabib wrote:
Hi,
Thanks for the clarification. So, now I am wondering how rank
information regarding processes in MPI_COMM_WORLD are assigned. Is
there a table that stores unique integer values for processess or is
rank assignment done in some other manner?
Thanks,
Sajjad Tabib
Tim Prins <tpr...@cs.indiana.edu>
Sent by: devel-boun...@open-mpi.org
11/30/07 07:22 AM
Please respond to
Open MPI Developers <de...@open-mpi.org>
To
Open MPI Developers <de...@open-mpi.org>
cc
Subject
Re: [OMPI devel] Using ompi_proc_t's proc_name.vpid as Universal rank
Hi Sajjad,
The vpid is not unique. If you do a comm_spawn then the newly launched
processes will have a new jobid, and their vpids will start at 0. So
the
whole process name is unique.
However, there is talk now of being able to join 2 jobs that were
started completely independently. This may lead to the point where a
process name is no longer unique, however this work appears to be a
ways
out and as far as I know no decisions have been made on it yet.
Hope this helps,
Tim
Sajjad Tabib wrote:
>
> Hello,
>
> I have a proprietary transport/messaging layer that sits below an
MTL
> component. This transport layer requires OpenMPI to assign it a rank
> that is unique and specific to that process and will not change from
> execution to termination. In a way, I am trying to find a one-one
> correspondence between a process's universal rank in OpenMPI and
this
> transport layer. I began looking at ompi_proc_t from different
processes
> and seemingly found a unique identifier, proc_name.vpid.
Consequently, I
> assigned the ranks to each process in my transport layer based on
the
> value of the local vpid of each process.
> I have not tested this thoroughly, but it has been working so far.
> Although, I would like to make sure that this is a good approach, or
> know, at least, whether if there are other ways to do this. I would
> appreciate it if you could leave me feedback or give suggestions
on how
> to assign universal ranks to a proprietary transport software.
>
> Thanks for your help,
>
> Sajjad Tabib
>
>
>
------------------------------------------------------------------------
>
> _______________________________________________
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
--
Jeff Squyres
Cisco Systems
