Howard,
I have no infinipath hardware, but the infinipath libraries are installed.
I tried to run with --mca mtl_psm_priority 0 instead of --mca mtl ^psm
but that did not work.
without psm mtl, I was unable to reproduce the persistent communication
issue,
so I concluded there was only one issue he
George,
What do you mean by "cvar version " ? Is there cvar version of
"coll_tuned_bcast_algorithm" ?
If you meant using cvar APIs then I use them. For example, in the following
example I use MPI_T_cvar_write to set the variable. Despite I can read
using MPI_T_cvar_read, the write does not work.
Gotcha; thanks.
> On Aug 14, 2015, at 2:12 PM, Howard Pritchard wrote:
>
> Hi Jeff,
>
> I don't know why Gilles keeps picking on the persistent request problem and
> mixing
> it up with this user bug. I do think for this user the psm probably is the
> problem.
>
>
> They don't have anythin
Hi Jeff,
I don't know why Gilles keeps picking on the persistent request problem and
mixing
it up with this user bug. I do think for this user the psm probably is the
problem.
They don't have anything to do with each other.
I can reproduce the persistent request problem on hopper consistently.
On Fri, Aug 14, 2015 at 1:56 PM, Jeff Squyres (jsquyres) wrote:
> Note, too, that these variables are likely only changeable before MPI_INIT.
>
> I didn't check these specific variables, but at least the
> btl_self_eager_limit variable is likely only read/used for setup during
> MPI_INIT. coll_t
Note, too, that these variables are likely only changeable before MPI_INIT.
I didn't check these specific variables, but at least the btl_self_eager_limit
variable is likely only read/used for setup during MPI_INIT.
coll_tuned_bcast_algorithm may only be used before a communicator is setup
(al
They are considered as control variables, so use the cvar version and you
should get them.
George.
On Fri, Aug 14, 2015 at 11:14 AM, Khalid Hasanov wrote:
> Hello,
>
> I am trying to use MPI_T interface to set *coll_tuned_bcast_algorithm*
> mca parameter during run time, however I was not su
Hmm. Oscar's not around to ask any more, but I'd be greatly surprised if he
had InfiniPath on his systems where he ran into this segv issue...?
> On Aug 14, 2015, at 1:08 PM, Howard Pritchard wrote:
>
> Hi Gilles,
>
> Good catch! Nate we hadn't been testing on a infinipath system.
>
> Howa
Hi Gilles,
Good catch! Nate we hadn't been testing on a infinipath system.
Howard
2015-08-14 0:20 GMT-06:00 Gilles Gouaillardet :
> Nate,
>
> i could get rid of the problem by not using the psm mtl.
> the infinipath library (used by the psm mtl) sets some signal handlers
> that conflict with
Hello,
I am trying to use MPI_T interface to set *coll_tuned_bcast_algorithm* mca
parameter during run time, however I was not successful to do that.
I wonder if is it currently supported in Open MPI.
I had the same problem with setting *btl_self_eager_limit *parameter.
The code I am using atta
Hi Ralph,
Thanks a lot for the fast reply and the clarification. We’ve re-added the
parameter to our MCA site configuration file.
Michael
On 14 Aug 2015, at 15:00 , Ralph Castain
mailto:r...@open-mpi.org>> wrote:
During the 1.7 series, we changed things at the request of system admins so
tha
This problem still exists in 1.8.8
On 06/29/2015 05:37 PM, Jeff Squyres (jsquyres) wrote:
Good catch; fixed.
Thanks!
On Jun 29, 2015, at 7:28 AM, Åke Sandgren wrote:
Hi!
static inline int ompi_mpi_errnum_is_class ( int errnum )
{
ompi_mpi_errcode_t *err;
if (errno < 0) {
During the 1.7 series, we changed things at the request of system admins so
that we don't oversubscribe allocations given to us by resource managers
unless specifically told to do so.
On Fri, Aug 14, 2015 at 12:52 AM, Schlottke-Lakemper, Michael <
m.schlottke-lakem...@aia.rwth-aachen.de> wrote:
Hi folks,
It seems like oversubscription is disabled by default in OpenMPI 1.8.7, at
least when running on a PBS/torque-managed node. When I run a program in
parallel on a node with 8 cores, I am not able to use more than 8 ranks:
> mic@aia272:~> mpirun --display-allocation -n 9 hostname
>
> =
Nate,
i could get rid of the problem by not using the psm mtl.
the infinipath library (used by the psm mtl) sets some signal handlers
that conflict with the JVM
that can be seen by running
mpirun -np 1 java -Xcheck:jni MPITestBroke data/
so instead of running
mpirun -np 1 java MPITestBroke dat
15 matches
Mail list logo
