When you MPI_COMM_SPAWN, the parent and children processes are said to be
"connected". And MPI_FINALIZE is collective across all connected processes
(see the definition of MPI_FINALIZE in MPI-2.2).
If you want to disconnect the spawned children from the parents, use
MPI_COMM_DISCONNECT. Then
Hello,
Traduzir do: português
Digite um texto ou
endereço de um site ou traduza um
documento.
Cancelar
Tradução do português
para inglês
I have three processes that communicate with each other. The first process
creates the other two processes (using MPI_Comm_spaw (...)).
When one of the proc
On 2011-08-31 7:26 PM, Jeff Squyres wrote:
On Aug 31, 2011, at 1:23 PM, Gus Correa wrote:
Hmmm ... maybe it was a mix of both?
From the very pen ... er ... keyboard (I-phone?, tablet?)
of Jeff Squyres:
http://www.open-mpi.org/community/lists/users/2010/10/14463.php
Good searching!
No, my dim
On Aug 31, 2011, at 1:23 PM, Gus Correa wrote:
> Hmmm ... maybe it was a mix of both?
> From the very pen ... er ... keyboard (I-phone?, tablet?)
> of Jeff Squyres:
> http://www.open-mpi.org/community/lists/users/2010/10/14463.php
Good searching!
No, my dim recollection has something to do with
Jeff Squyres wrote:
On Aug 31, 2011, at 12:13 PM, Gus Correa wrote:
Do you want to add this kind of info to the FAQ? I seem to recall that the
gettimeofday question has come up before...?
Indeed, but often related to the accuracy of the MPI_Wtime clock, IIRR.
No, I have a dim recollection
On Aug 31, 2011, at 12:13 PM, Gus Correa wrote:
>> Do you want to add this kind of info to the FAQ? I seem to recall that the
>> gettimeofday question has come up before...?
>
> Indeed, but often related to the accuracy of the MPI_Wtime clock, IIRR.
No, I have a dim recollection that it came u
Jeff Squyres wrote:
Shiqing --
Do you want to add this kind of info to the FAQ?
I seem to recall that the gettimeofday question has come up before...?
Indeed, but often related to the accuracy of the MPI_Wtime clock, IIRR.
Gus Correa
On Aug 31, 2011, at 8:27 AM, Shiqing Fan wrote:
Hi
That seems like a bug to me.
What version of Open MPI are you using? How have you setup the C/R
functionality (what MCA options do you have set, what command line
options are you using)? Can you send a small reproducing application
that we can test against?
That should help us focus in on the pro
Shiqing --
Do you want to add this kind of info to the FAQ? I seem to recall that the
gettimeofday question has come up before...?
On Aug 31, 2011, at 8:27 AM, Shiqing Fan wrote:
> Hi Fabien,
>
> The GCC build under MinGW is not supported in Open MPI 1.4.3. The initial
> support is now in t
Hi Fabien,
The GCC build under MinGW is not supported in Open MPI 1.4.3. The
initial support is now in trunk, but needs more test.
Actually, you may also try building 1.4.3 with Visual Studio Express
with Fortran bindings for gfortran. Just configure the solution for
Visual Studio, and speci
Dear Group,
I have a mpi-program in which every process is communicating with its
neighbors. When SELF-checkpointing, every process writes to a separate
file.Problem is that sometimes after making a checkpoint, program does not
continue again. Having more number of processes makes this problem
11 matches
Mail list logo
