Just an FYI that this issue has been found and fixed and will be available in
the next release.
https://github.com/open-mpi/ompi-release/pull/357
Rolf
From: Rolf vandeVaart
Sent: Wednesday, July 01, 2015 4:47 PM
To: us...@open-mpi.org
Subject: RE: [OMPI users] 1.8.6 w/ CUDA 7.0 & GDR Huge Memory
Have you checked where the procs are actually bound? I’m wondering if you don’t
wind up somehow with a proc bound to cores on different sockets
> On Jul 6, 2015, at 7:06 AM, Saliya Ekanayake wrote:
>
> Just checking if anyone has experienced a similar situation or has any
> pointers to underst
Just checking if anyone has experienced a similar situation or has any
pointers to understand this.
Thank you
Saliya
On Jul 1, 2015 9:27 PM, "Saliya Ekanayake" wrote:
> Hi,
>
> I am getting strange performance results for allgatherv operation for the
> same number of procs and data, but with var
George,
I got confused since from bitbucket, ulfm was imported from svn r25756 and
this svn id comes from the v1.7 branch
Also, orte_job_map_t has a policy field in v1.6 but no more in v1.7
Anyway, you obviously know ulfm better than me, so I was wrong
Cheers,
Gilles
On Monday, July 6, 2015, G
Thank you both for your feedback!
It now compiles. I have also subscribed to the correct mailing list.
Slainte!
Rafael Lago
On Monday 06 July 2015 08:15:33 George Bosilca wrote:
> Gilles thanks for your feedback, but I need to correct your claim: ULFM is
> based on 1.6.
>
> George.
>
>
> On M
Gilles thanks for your feedback, but I need to correct your claim: ULFM is
based on 1.6.
George.
On Mon, Jul 6, 2015 at 8:11 AM, Gilles Gouaillardet <
gilles.gouaillar...@gmail.com> wrote:
> Rafael,
>
> At first glance, ulfm is based on openmpi 1.7
> But the poe plm was written for openmpi 1.
Rafael,
At first glance, ulfm is based on openmpi 1.7
But the poe plm was written for openmpi 1.6
You'd better ask the ulfm folks about this issue
Cheers,
Gilles
On Monday, July 6, 2015, Rafael Lago wrote:
> Hello there!
> I'm trying to work in a fault-tolerance project, and I immediately go
Rafael,
Add "--enable-mca-no-build=plm-poe" to your configure line. This should
disable the POE PLM, which I don't think works in the context of ULFM
anyway.
That being said, ULFM is a separate effort from Open MPI, you should ask
your questions on the ULFM mailing lists (
http://fault-tolerance.
Hello there!
I'm trying to work in a fault-tolerance project, and I immediately got
interested in the ULFM extension of OpenMPI. Although I've managed to compile
and install OpenMPI-1.8.6 without a problem, I have been failing so far to
compile ULFM.
I am trying to follow the instructions in
h
