Re: [OMPI users] SOLVED hybrid programming: cpu load issues

SOLVED: Thank you Ralph for your clarification: I realized that the problem was due to some my wrong command but I was not able to figure out where was the error! So I can use hybrid programming on my cluster. Thank you to all, Fedele Il giorno ven, 26/06/2015 alle 04.42 -0700, Ralph Castain ha

[OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

Hi! static inline int ompi_mpi_errnum_is_class ( int errnum ) { ompi_mpi_errcode_t *err; if (errno < 0) { return false; } I assume it should be errnum < 0. -- Ake Sandgren, HPC2N, Umea University, S-90187 Umea, Sweden Internet: a...@hpc2n.umu.se Phone: +46 90 7866134

Re: [OMPI users] Error while launching Jobs in LSF with OpenMPI

Thank you Ralph. Are there any known issues with using the LSF wrapper script mpirun.lsf to launch openmpi runs in RHEL6 ? I will also try to get openmpi updated. Thanks, Rahul On Wed, Jun 24, 2015 at 3:38 PM, Ralph Castain wrote: > You probably should update to OMPI 1.8.6

Re: [OMPI users] Progress on target of MPI_Win_lock on Infiniband

This is not a configuration issue. On 1.8.x and master we use two-sided communication to emulation one-sided. Since we do not currently have async progress this requires the target to call into MPI to progress RMA communication. This will change in 2.x. I will be adding a new component that does

[OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Hi! The my_sense entity in struct ompi_osc_sm_module_t is protected by OPAL_HAVE_POSIX_THREADS in the definition (ompi/mca/osc/sm/osc_sm.h) But in ./ompi/mca/osc/sm/osc_sm_active_target.c it is not. (Tripped on this due to a compiler problem which caused it to only partially detect threads

Re: [OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

I see a typo. You are checking errno instead of errnum. -Nathan On Mon, Jun 29, 2015 at 01:28:11PM +0200, Åke Sandgren wrote: > Hi! > > static inline int ompi_mpi_errnum_is_class ( int errnum ) > { > ompi_mpi_errcode_t *err; > > if (errno < 0) { > return false; > } > > I

Re: [OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

That's what i said. The code in openmpi checks errno and not errnum. On 06/29/2015 05:27 PM, Nathan Hjelm wrote: I see a typo. You are checking errno instead of errnum. -Nathan On Mon, Jun 29, 2015 at 01:28:11PM +0200, Åke Sandgren wrote: Hi! static inline int ompi_mpi_errnum_is_class (

Re: [OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

Hah, my bad. Didn't look at the function name. Will fix. -Nathan On Mon, Jun 29, 2015 at 05:31:01PM +0200, Åke Sandgren wrote: > That's what i said. The code in openmpi checks errno and not errnum. > > On 06/29/2015 05:27 PM, Nathan Hjelm wrote: > > > >I see a typo. You are checking errno

Re: [OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

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) { >return false; >} > > I assume it should be

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Open MPI has required posix threads for some time. The check for OPAL_HAVE_POSIX_THREADS in ompi/mca/osc/sm/osc_sm.h is stale and should be removed. I will clean that out in master, 1.8, and 1.10. -Nathan On Mon, Jun 29, 2015 at 05:26:30PM +0200, Åke Sandgren wrote: > Hi! > > The my_sense

Re: [OMPI users] Bug in ompi/errhandler/errcode.h (1.8.6)?

The interesting thing is that gcc/intel/portland all failed to detect this. Pathscale found it, and clang probably would. 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!

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Yeah, i thought so. Well code reductions are good when correct :-) On 06/29/2015 05:39 PM, Nathan Hjelm wrote: Open MPI has required posix threads for some time. The check for OPAL_HAVE_POSIX_THREADS in ompi/mca/osc/sm/osc_sm.h is stale and should be removed. I will clean that out in master,

Re: [OMPI users] Progress on target of MPI_Win_lock on Infiniband

Hi Nathan, > This is not a configuration issue. On 1.8.x and master we use two-sided > communication to emulation one-sided. Since we do not currently have > async progress this requires the target to call into MPI to progress RMA > communication. thanks for the clarification. Is there special

Re: [OMPI users] OpenMPI 1.8.6, CentOS 6.3, too many slots = crash

Would the output of dmidecode -t processor and/or lstopo tell me conclusively if hyperthreading is enabled or not? Hyperthreading is supposed to be enabled for all the IBM x3550 M3 and M4 nodes, but I'm not sure if it actually is and I don't have access to the BIOS settings. -Bill L.

Re: [OMPI users] OpenMPI 1.8.6, CentOS 6.3, too many slots = crash

I think so, yes. On Mon, Jun 29, 2015 at 3:42 PM, Lane, William wrote: > Would the output of dmidecode -t processor and/or lstopo tell me > conclusively > if hyperthreading is enabled or not? Hyperthreading is supposed to be > enabled > for all the IBM x3550 M3 and M4

Re: [OMPI users] OpenMPI 1.8.6, CentOS 6.3, too many slots = crash

lstopo will tell you -- if there is more than one "PU" (hwloc terminology for "processing unit") per core, then hyper threading is enabled. If there's only one PU per core, then hyper threading is disabled. > On Jun 29, 2015, at 4:42 PM, Lane, William wrote: > > Would

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Nathan, I removed all of this (including the --with-threads configure option) on master a while ago. because this is a change in the configure command line, I never made a PR for v1.8 Cheers, Gilles On Tuesday, June 30, 2015, Nathan Hjelm wrote: > > Open MPI has required

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Ah, that would explain why I am not seeing it in master. Can you PR the changes to v1.10? -Nathan On Tue, Jun 30, 2015 at 07:06:15AM +0900, Gilles Gouaillardet wrote: >Nathan, >I removed all of this (including the --with-threads configure option) on >master a while ago. >because

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

Nathan, Shall I remove the --with-threads configure option ? or make it dummy ? Cheers, Gilles On Tuesday, June 30, 2015, Nathan Hjelm wrote: > > Ah, that would explain why I am not seeing it in master. Can you PR the > changes to v1.10? > > -Nathan > > On Tue, Jun 30, 2015

Re: [OMPI users] my_sense in ompi_osc_sm_module_t not always protected by OPAL_HAVE_POSIX_THREADS

I would remove it since it has no effect in 1.10. -Nathan On Tue, Jun 30, 2015 at 07:16:09AM +0900, Gilles Gouaillardet wrote: >Nathan, >Shall I remove the --with-threads configure option ? >or make it dummy ? >Cheers, >Gilles > >On Tuesday, June 30, 2015, Nathan Hjelm