[OMPI users] Call to MPI_Test has large time-jitter

Hi, I recently started on an MPI-based, 'real-time', pipelined-processing application, and the application fails due to large time-jitter in sending and receiving messages. Here are related info -   1) Platform: a) Intel Box: Two Hex-core, Intel Xeon, 2.668 GHz (...total of 12 cores), b) OS: SUS

Re: [OMPI users] Using (or not using) Torque/Moab under PBS Pro as the OpenMPI launcher

You can build openMPI without tm, which will disable it, or you can test first with a nasty option like: mpirun \ --mca plm ^tm \ --mca ras ^tm \ --hostfile $PBS_NODEFILE \ ./testmom Brock Palen www.umich.edu/~brockp Center for Adva

[OMPI users] Using (or not using) Torque/Moab under PBS Pro as the OpenMPI launcher

Hi, At Cray, we have a a Cluster Compatibility Mode (CCM) which runs under PBSPro. If we do a qsub, we get an allocation of compute nodes and the first node in the list of allocated nodes is considered the "head node" of the "Cluster". The list of allocated nodes is contained i

Re: [OMPI users] MPI-IO problem

On Wed, Dec 15, 2010 at 01:21:35PM -0800, Tom Rosmond wrote: > I want to implement an MPI-IO solution for some of the IO in a large > atmospheric data assimilation system. Years ago I got some small > demonstration Fortran programs ( I think from Bill Gropp) that seem to > be good candidate protot

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

John, Thanks, more info below. Le 17/12/2010 17:32, John Hearns a écrit : On 17 December 2010 15:47, Gilbert Grosdidier wrote: gg= I don't know, and firmware_revs does not seem to be available. Only thing I got on a worker node was with lspci : If you log into a compute node the command i

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

On 17 December 2010 15:47, Gilbert Grosdidier wrote: >> > gg= I don't know, and firmware_revs does not seem to be available. > Only thing I got on a worker node was with lspci : If you log into a compute node the command is /usr/sbin/ibstat The firmware_revs command is on the cluster admin

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

Bonjour John, First, Thanks for your feedback. Le 17 déc. 10 à 16:13, John Hearns a écrit : On 17 December 2010 14:45, Gilbert Grosdidier wrote: Bonjour, About this issue, for which I got NO feedback ;-) Gilbert, as you have an SGI cluster, have you filed a support request to SGI? gg

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

On 17 December 2010 14:45, Gilbert Grosdidier wrote: > Bonjour, >  About this issue, for which I got NO feedback ;-) I recently spotted > into btl_openib.c code, that this error message could come from On the cluster admin node, run firmware_revs and look for the Infiniband firmware

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

On 17 December 2010 14:45, Gilbert Grosdidier wrote: > Bonjour, >  About this issue, for which I got NO feedback ;-) Gilbert, as you have an SGI cluster, have you filed a support request to SGI? Also, which firmware do you have installed? I haveFirmware version: 2.5.0 http://www.open

Re: [OMPI users] Issue with : btl_openib.c (OMPI 1.4.3)

Bonjour, About this issue, for which I got NO feedback ;-) I recently spotted into btl_openib.c code, that this error message could come from some missing ConnectX HCA ibv_resize_cq function. Well ... I was unable yet to figure out why/how this could occur, but I have a now a closely related q

[OMPI users] [SPAM:### 82%] RE: [SPAM:### 89%] OpenMPI LAM ?

Oups ! I got it ... One of my slaves has been compiled with a bad mpif77 (one mpif77 coming with an old Lam installation provided by Portland PGI). So I rectified my Path to have the correct mpif77, and it's much better Sorry for this mistake and thank you for your help Pierre -Message d'or

[OMPI users] [SPAM:### 82%] RE: [SPAM:### 89%] OpenMPI LAM ?

Thank you Ricardo for your answer. Actually, I use only local nodes for this test. And on this node, I have : $mpirun --version mpirun (Open MPI) 1.4.3 I keep on searching... Pierre -Message d'origine- De : users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] De la part de

Re: [OMPI users] [SPAM:### 89%] OpenMPI LAM ?

On Fri, 17 Dec 2010, GUBERNATIS Pierre 164999 wrote: Hello, I am new at Openmpi : I used Lam so far and we have just installed OpenMpi. When I run "mpirun -app schema" , OpenMpi complains about a missing daemon lamd, whereas the documentations says there is no need to run lamboot anymore.

[OMPI users] [SPAM:### 89%] OpenMPI LAM ?

Hello, I am new at Openmpi : I used Lam so far and we have just installed OpenMpi. When I run "mpirun -app schema" , OpenMpi complains about a missing daemon lamd, whereas the documentations says there is no need to run lamboot anymore. To make sure : $ which mpirun /export/opt/OPEN-MPI

Re: [OMPI users] [SPAM:### 85%] Re: [SPAM:### 83%] problem when compiling ompenmpiV1.5.1

Hi, the header file 'omp.h' belongs to the compiler, so if OpenMP is enabled by a specific compiler option (e.g. '-fopenmp' for GNU) the compiler should actually know where the header file is located. There is no need to install any additional OpenMP packages. The header include at the indicat