No, it doesn't matter at all for OMPI - any order is fine. The issue I see is
that your mpiexec isn't the OMPI one, but is from someone else. I have no idea
whose mpiexec you are using
On Sep 24, 2014, at 6:38 PM, XingFENG wrote:
> I have found the solution. The command mpirun -machinefile ./
I have found the solution. The command *mpirun -machinefile ./my_hosts -n 3
./testMPI* works. I think the order of arguments matters here.
On Thu, Sep 25, 2014 at 11:02 AM, XingFENG wrote:
> Hi all,
>
> I got problem with running program on a cluster.
> I used the following command. *my_hosts* i
Hi all,
I got problem with running program on a cluster.
I used the following command. *my_hosts* is a file containing 3 hosts while
*testMPI* is a very simple MPI program.
==
*mpirun -np 2 --hostfile ./my_hosts ./testMPImpirun -np 2 --machinefile
./my_ho
On Wed, 24 Sep 2014, Ralph Castain wrote:
As I said, we removed the warning starting in 1.8.3
On Sep 24, 2014, at 1:23 PM, Brock Palen wrote:
So very hetero, I did some testing and I couldn't make it happen
below 32 cores. Not sure if this the real issue [...]
Just to amplify Ralph's resp
As I said, we removed the warning starting in 1.8.3
On Sep 24, 2014, at 1:23 PM, Brock Palen wrote:
> So very hetero, I did some testing and I couldn't make it happen below 32
> cores. Not sure if this the real issue or if it requires a specific layout:
>
> [brockp@nyx5512 ~]$ cat $PBS_NODEFI
So very hetero, I did some testing and I couldn't make it happen below 32
cores. Not sure if this the real issue or if it requires a specific layout:
[brockp@nyx5512 ~]$ cat $PBS_NODEFILE | sort | uniq -c
1 nyx5512
1 nyx5515
1 nyx5518
1 nyx5523
1 nyx5527
2 nyx
Hi!
I want to convert the input/output of my program to MPI-IO routines. To
write the same data, as is written in the already implement textmode
routines, I need a custom datatype consisting of several integers and reals.
While investigating the functionality, I created a module, which cares for
