seq
> This will cause OMPI to map the process ranks according to the order in the
> hostfile. You need to specify one line for each node/rank, just as you have
> done.
> Ralph
>
> On Fri, Jun 19, 2009 at 10:24 PM, Rajesh Sudarsan
> wrote:
>>
>> Hi Ralph,
>>
>
you do a --display-map and send
> it along, I might be able to spot the issue.
> Thanks
> Ralph
>
> On Fri, Jun 19, 2009 at 1:35 PM, Rajesh Sudarsan
> wrote:
>>
>> Hi,
>>
>> I tested a simple hello world program on 5 nodes each with dual
>> quad
Hi,
I tested a simple hello world program on 5 nodes each with dual
quad-core processors. I noticed that openmpi does not always follow
the order of the processors indicated in the machinefile. Depending
upon the number of processors requested, openmpi does some type of
sorting to find the best no
As a followup to my problem, I tested this sample code with LAM/MPI and it
worked perfectly without any segmentation faults. Has any one tried this
and faced this isue? Any help will be appreciated.
Regards,
Rajesh
-- Forwarded message --
From: Rajesh Sudarsan
List-Post: users
Hi,
I am trying to write a simple code which does the following -
A master process running on 'n' processors spawn 4 processes using the
MPI_Comm_spawn_multiple command. After spawning, the intercommunicator
between the master and the spawned processes are merged using
MPI_Intercomm_merge to create
Hi,
I have simple MPI program that uses MPI_comm_spawn to create additional
child processes.
Using MPI_Intercomm_merge, I merge the child and the parent
communicator resulting in a single expanded user
defined intracommunicator. I know MPI_COMM_WORLD is a constant which is
statically initialized
