Dear Jody,
WRF is running well on serial option (i.e single interface) . I am running
another application HRM using OpenMPI , there is no issue with that and
application is running on cluster of many nodes. The wrf manual says the
following about MPI run:
I*f you have run the model on multiple pr
Could you re-enable the SL param (btl_openib_ib_service_level) for
RoCE? Jeff was kind enough to provide a patch to let me specify the
gid_index, but that doesn't seem to be working. To get RoCE to work
correctly (at least, on Nexus switches) I'll need to specify both a
gid_index and an IB servic
On Feb 22, 2011, at 4:41 PM, Prentice Bisbal wrote:
> One of the researchers I support is writing some Fortran code that uses
> Open MPI. The code is being compiled with the Intel Fortran compiler.
> This one line of code:
>
> integer ierr,istatus(MPI_STATUS_SIZE)
>
> leads to these errors:
>
>
On 2/22/2011 1:41 PM, Prentice Bisbal wrote:
One of the researchers I support is writing some Fortran code that uses
Open MPI. The code is being compiled with the Intel Fortran compiler.
This one line of code:
integer ierr,istatus(MPI_STATUS_SIZE)
leads to these errors:
$ mpif90 -o simplex sim
One of the researchers I support is writing some Fortran code that uses
Open MPI. The code is being compiled with the Intel Fortran compiler.
This one line of code:
integer ierr,istatus(MPI_STATUS_SIZE)
leads to these errors:
$ mpif90 -o simplex simplexmain579m.for simplexsubs579
/usr/local/open
On Feb 22, 2011, at 11:06 AM, Bill Rankin wrote:
> Try putting an "MPI_Barrier()" call before your MPI_Finalize() [*]. I
> suspect that one of the programs (the sending side) is calling Finalize
> before the receiving side has processed the messages.
FWIW: I have rarely seen this to be the is
Yes, I tried to add MPI_Barrier and it didn't work. The output is the
same with the code without MPI_Barrier.
Any more thoughts?
Thanks!
Kong
On Tue, Feb 22, 2011 at 12:23 PM, Bill Rankin wrote:
>> Hi,
>>
>> Thanks for the reply. But this can not solve the problem.
>
> Not sure if this was not
Hi Ahsan, Jody
Just a guess that this may be a stack size problem.
Did you try to run WRF with unlimited stack size?
Also, does your machine have enough memory to run WRF?
I hope this helps,
Gus Correa
jody wrote:
Hi
At a first glance i would say this is not a OpenMPI problem,
but a wrf probl
On Feb 18, 2011, at 8:59 AM, Toon Knapen wrote:
> (Probably this issue has been discussed at length before but unfortunately I
> did not find any threads (on this site or anywhere else) on this topic, if
> you are able to provide me with links to earlier discussions on this topic,
> please do n
> Hi,
>
> Thanks for the reply. But this can not solve the problem.
Not sure if this was not your intended meaning (using "can not" instead of "did
not"), but did you try it?
> The output indicate that both nodes hang at the second MPI_Wait, and
> no one can reaches the MPI_Finalize.
Flushing
Hi,
Thanks for the reply. But this can not solve the problem.
The output indicate that both nodes hang at the second MPI_Wait, and
no one can reaches the MPI_Finalize.
>> >> ***
>> >> Hello from processor 0 of 2
>> >>
>> >> Received one message
>> >>
>>
I think Bill is right. Here is the description for mpi_finalize:
This routine cleans up all MPI states. Once this routine is called, no MPI
routine (not even MPI_Init) may be called, except for MPI_Get_version,
MPI_Initialized, and MPI_Finalized. Unless there has been a call to
MPI_Abort, you mus
Try putting an "MPI_Barrier()" call before your MPI_Finalize() [*]. I suspect
that one of the programs (the sending side) is calling Finalize before the
receiving side has processed the messages.
-bill
[*] pet peeve of mine : this should almost always be standard practice.
> -Original M
Hi, Thank you for the reply.
However, using MPI_waitall instead of MPI_wait didn't solve the
problem. The code would hang at the MPI_waitall. Also, I'm not quit
understand why the code is inherently unsafe. Can the non-blocking
send or receive cause any deadlock?
Thanks!
Kong
On Mon, Feb 21, 2
Hi
At a first glance i would say this is not a OpenMPI problem,
but a wrf problem (though io must admit i have no knowledge whatsoever ith wrf)
Have you tried running a single instance of wrf.exe?
Have you tried to run a simple application (like a "hello world") on your nodes?
Jody
On Tue, Feb
Hi Ralf,
I've tested spawning with the OpenMPI 1.5 release but that fix is not there.
Are you sure you've added it ?
Thank you,
Federico
2010/10/19 Ralph Castain
> The fix should be there - just didn't get mentioned.
>
> Let me know if it isn't and I'll ensure it is in the next one...but I'd
Hello,
I an stuck in a problem that is regarding the running for Weather research
and Forecasting Model (WRFV 3.2.1). I get the following error while running
with mpirun. Any help would be highly appreciated.
*[pmdtest@pmd02 em_real]$ mpirun -np 4 wrf.exe
starting wrf task 0 of 4
starting wrf t
17 matches
Mail list logo