On Fri, 3 Feb 2017, r...@open-mpi.org wrote:
I do see a diff between 2.0.1 and 2.0.2 that might have a related
impact. The way we handled the MCA param that specifies the launch agent
(ssh, rsh, or whatever) was modified, and I don’t think the change is
correct. It basically says that we don’t
Hi Michel,
Could you try running the app with
export TMPDIR=/tmp
set in the shell you are using?
Howard
2017-02-02 13:46 GMT-07:00 Michel Lesoinne :
Howard,
First, thanks to you and Jeff for looking into this with me. 👍
I tried ../configure --disable-shared --enable-static --prefix ~/.local
Hi all,
My apologies for not replying sooner on this issue - I’ve been swamped with
other tasking. Here’s my latest:
1.) I have looked deep into bindings on both systems (used --report-bindings
option) and nothing came to light. I’ve tried multiple variations on bindings
settings and only mi
“c.) the workstation is hyper threaded and cluster is not”
You might turn off hyperthreading (HT) on the workstation, and re-run.
I’ve seen some OS’s on some systems get confused and assign multiple OS “cpus”
to the same HW core/thread.
In any case, if you turn HT off, and top shows you that tas
On Mon, 6 Feb 2017, Mark Dixon wrote:
...
Ah-ha! "-mca plm_rsh_agent foo" fixes it!
Thanks very much - presumably I can stick that in the system-wide
openmpi-mca-params.conf for now.
...
Except if I do that, it means running ompi outside of the SGE environment
no longer works :(
Should I j
Thanks, Tom. I did try using the mpirun —bind-to-core option and confirmed
that individual MPI processes were placed on unique cores (also without other
interfering MPI runs); however, it did not make a significant difference. That
said, I do agree that turning off hyper-threading is an import
Hi,
We recently noticed openmpi is using btl openib over self,sm for single node
jobs, which has caused performance degradation for some applications, e.g.
'cp2k'. For opempi version 2.0.1, our test shows single node 'cp2k' job using
openib is ~25% slower than using self,sm. We advise users do
Hi Howard!
Good news. This makes things work finally.
Thanks.
I think however that it should not be necessary, but if I have to do that
every time, I guess I will 👍
On Mon, Feb 6, 2017 at 8:09 AM, Howard Pritchard
wrote:
> Hi Michel,
>
> Could you try running the app with
>
> export TMPDIR=/tmp
