Hi all,
I have built OpenMPI 1.10.2 with RoCE network support on our test
cluster. On the cluster we use lmod to manage paths to different
versions of softwares. The problem I have is that I receive the "orted:
command not found" message given that the path to the orted binary is
not exported to th
Hi all,
In our cluster the nodes are interconnected with RoCE and I want to set
up OpenMPI to run on it via SLURM.
I initially compiled OpenMPI 1.10.2 only with IB verbs support and I
have no problem making it run over RoCE.
Then I have successfully built it with SLURM support as follows:
./config
efault
>
> Cheers,
>
> Gilles
>
> On 3/4/2016 7:22 AM, Davide Vanzo wrote:
> > Hi all,
> > I have built OpenMPI 1.10.2 with RoCE network support on our test
> > cluster. On the cluster we use lmod to manage paths to different
> > versions of softwares. The proble
I solved the problem. For some reason the
OMPI_MCA_btl_openib_cpc_include environment variable was set to udcm
during the tests. By ensuring that it is set to rdmacm solved the
issue.
Thanks anyway!
Davide
On Thu, 2016-03-03 at 16:40 -0600, Davide Vanzo wrote:
> Hi all,
> In our cluster the