You have version confusion somewhere - the error message indicates that
mpirun is looking for a component that only exists in the 1.2.x series, not
in 1.3.x. Check that your LD_LIBRARY_PATH is pointing to the 1.3.2 location,
along with your PATH.
On Fri, May 29, 2009 at 12:52 PM, Jeff Layton wr
I've got some more information (after rebuilding Open MPI and the
application a few times). I put
-mca mpi_show_mca_params enviro
in my mpirun line to get some of the parameter information back.
I get the following information back (warning - it's long).
---
vasilis wrote:
The original issue, still reflected by the subject heading of this e-mail,
was that a message overran its receive buffer. That was fixed by using
tags to distinguish different kinds of messages (res, jacob, row, and col).
I thought the next problem was the small (10^-
Good morning,
I just built 1.3.2 on a ROCKS 4.something system. I built my code
(CFL3D) with the Intel 10.1 compilers. I also linked in the
OpenMPI libs and the Intel libraries to make sure I had the paths
correct. When I try running my code, I get the following,
error: executing task of job 29
> The original issue, still reflected by the subject heading of this e-mail,
> was that a message overran its receive buffer. That was fixed by using
> tags to distinguish different kinds of messages (res, jacob, row, and col).
>
> I thought the next problem was the small (10^-10) variations in
Hi Mr. Jeff Squyres,
Is it true to use bidirectianal communication with MPI in ethernet Cluster?
I have tried once (I thought, it is possible because of fully duplex swithes).
However, I could not get bandwidth improvement as I was expecting.
If you answer is YES, would you please tell me about p
