>
>> Perhaps if someone could run this test again with --report-bindings
>> --leave-session-attached and provide -all- output we could verify that
>> analysis and clear up the confusion?
>>
> Yeah, however I bet you we still won't see output.
Actually, it seems we do get more output! Results
Dear all,
I am trying to disable the eager mode in OpenMPI 1.3.3 and I don't see a
real difference between the timings.
I would like to execute a ping (rank 0 sends a message to rank 1) and to
measure the duration of the MPI_Send on rank 0 and the duration of
MPI_Recv on rank 1. I have the fol
Hi,
I found that ./openmpi-1.4.3/ompi/runtime/ompi_mpi_init.c was changed.
Calling opal_progress_event_users_decrement was deleted as below.
$diff openmpi-1.4.2/ompi/runtime/ompi_mpi_init.c openmpi-1.4.3
/ompi/runtime/ompi_mpi_init.c
813,819d812
< /* Undo ORTE calling opal_progress_event_user
We just discovered this ticket, which might describe the same problem that
we have:
https://svn.open-mpi.org/trac/ompi/ticket/1505
It seems unresolved... do you have a workaround for it? I've seen the "-mca
opal_net_private_ipv4 " parameter, but I don't exactly know how to use it...
At least my e
Yes, I believe this solves the mystery. In short OGE and ORTE both
work. In the linear:1 case the job is exiting because there are not
enough resources for the orte binding to work, which actually makes
sense. In the linear:2 case I think we've proven that we are binding to
the right amount
Hi,
One typically uses mpirun to launch a set of mpi processes.
Is there some programmatical interface to launching the runtime and having
the process that launched the runtime becoming part of the list of mpi
processes,
Regards,
Am 18.11.2010 um 11:57 schrieb Terry Dontje:
> Yes, I believe this solves the mystery. In short OGE and ORTE both work. In
> the linear:1 case the job is exiting because there are not enough resources
> for the orte binding to work, which actually makes sense. In the linear:2
> case I think
Hi there,
Thanks for the expedite reply. The thing is that although the mpirun is
setup correctly (since a simple hello world works), when I run the main
SWMF.exe executable, the cluster machines somehow fail to find the
executable (SWMF.exe).
So, I have attached the sample error file from one of
Is you "hello world" test program in the same directory as SWMF? Is it
possible that the path you are specifying is not available on all of the
remote machines? That's the most common problem we see.
On Thu, Nov 18, 2010 at 7:59 AM, Tushar Andriyas wrote:
> Hi there,
>
> Thanks for the expedite
no its not in the same directory as SWMF. I guess the path is the same since
all the machines in a cluster are configured d same way. How do I know if
this is not the case?
On Thu, Nov 18, 2010 at 8:25 AM, Ralph Castain wrote:
> Is you "hello world" test program in the same directory as SWMF? Is
You can qsub a simple "ls" on that path - that will tell you if the path is
valid on all machines in that allocation.
What typically happens is that home directories aren't remotely mounted, or
are mounted on a different location.
On Thu, Nov 18, 2010 at 8:31 AM, Tushar Andriyas wrote:
> no its
you could spawn more processes from currently running processes.
On Thu, Nov 18, 2010 at 3:05 AM, Hicham Mouline wrote:
> Hi,
>
> One typically uses mpirun to launch a set of mpi processes.
>
> Is there some programmatical interface to launching the runtime and having
> the process that launche
Try lowering the eager threshold more gradually... e.g., 4K, 2K, 1K,
512, etc. -- and watch what happens. I think you will see what you
expect, except once you get too small then the value is ignored
entirely. So, the setting just won't work at the extreme value (0) you
want.
Maybe the thin
Dear,
I'm using Mellanox infiniband network card and trying to run it with
openmpi.
The problem is that I can connect and communicate between nodes, but I'm not
sure whether it is in a correct state or not.
I have two version of openmpi, one is compiled with mca-btl-openib and the
other is withou
14 matches
Mail list logo
