Juan,
You also need to make sure knem and MOFED drivers are loaded on all the
compute nodes.
You also need to double check the permissions of /dev/knem
Cheers,
Gilles
On Wednesday, January 18, 2017, Juan A. Cordero Varelaq <
bioinformatica-i...@us.es> wrote:
> Sure, I attach the config.log fro
On Tue, Jan 17, 2017 at 09:56:54AM -0800, r...@open-mpi.org wrote:
> As I recall, the problem was that qrsh isn???t available on the backend
> compute nodes, and so we can???t use a tree for launch. If that isn???t true,
> then we can certainly adjust it.
>
qrsh should be available on all nodes o
Hi,
knem and MOFED drivers are installed in /opt:
* /opt/knem-1.1.90mlnx2
* /opt/mellanox/fca
* /opt/mellanox/mxm
* /opt/mellanox/openshmem
However/dev/knem does not exist.
Cheers,
Juan
On 18/01/17 11:36, Gilles Gouaillardet wrote:
Juan,
You also need to make sure knem and MOFED driver
Juan,
So you need to load the knem module
sudo modprobe knem
and then you can check it is correctly loaded with lsmod
Loading the module should automagically create /dev/knem, but maybe not
with the permissions you expect
Cheers,
Gilles
On Wednesday, January 18, 2017, Juan A. Cordero Varelaq <
Hi,
when I try sudo modprobe knem, I get:
FATAL: Error inserting knem
(/lib/modules/3.13.0-37-generic/updates/dkms/knem.ko): Invalid module format
Cheers,
Juan
On 18/01/17 15:08, Gilles Gouaillardet wrote:
Juan,
So you need to load the knem module
sudo modprobe knem
and then you can check i
Hi,
We have a tool where all workers will use MPI_File_write_shared() on a
file that was opened with MPI_MODE_APPEND, mostly because rank 0 will
have written some format specific header data.
We recently upgraded our openmpi version from v1.10.4 to v2.0.1. And
at that time we noticed a behaviour
I will look into this, I have a suspicion on what might be wrong. Give
me a day or three.
Thanks
EDgar
On 1/18/2017 9:36 AM, Nicolas Joly wrote:
Hi,
We have a tool where all workers will use MPI_File_write_shared() on a
file that was opened with MPI_MODE_APPEND, mostly because rank 0 will
h
If compiling with -O0 solves the problem, then you should use -assume
protect-parens and/or one of the options discussed in the PDF you will find
at
https://software.intel.com/en-us/articles/consistency-of-floating-point-results-using-the-intel-compiler.
Disabling optimization is a heavy hammer tha
Hi Oscar,
I have similar issues that I was never able to fully track down in my code,
but I think you just identified the real problem. If you figure out the
correct options could you please let me know here?
Using the compiler optimizations are important for our code, but if we can
solve this is
