Re: [OMPI users] Help configuring openmpi

2008-05-14 Thread JUAN CARLOS LARROYA HUGUET
quot;Open MPI Users" > Copie à : > Objet : Re: [OMPI users] Help configuring openmpi > > On May 13, 2008, at 3:15 PM, Juan Carlos Larroya Huguet wrote: > > > Thanks very much Jeff, you solved my problem. The new CPU times are > > correct. > > Good! >

Re: [OMPI users] Help configuring openmpi

2008-05-13 Thread Jeff Squyres
On May 13, 2008, at 3:15 PM, Juan Carlos Larroya Huguet wrote: Thanks very much Jeff, you solved my problem. The new CPU times are correct. Good! PS: I was working with openmpi 1.2.5, to test your suggestion I moved to version 1.2.6... I tried to install openmpi in my own path using config

Re: [OMPI users] Help configuring openmpi

2008-05-13 Thread Juan Carlos Larroya Huguet
Hi, Thanks very much Jeff, you solved my problem. The new CPU times are correct. output.000: temps apres petits calculs =161.828640937805 output.001: temps apres petits calculs =167.412606000900 output.002: temps apres petits calculs =161.822407007217 output.003: temps

Re: [OMPI users] Help configuring openmpi

2008-05-12 Thread Jeff Squyres
If OMPI is spinning consuming 100% of your CPU, it usually means that some MPI function call is polling waiting for completion. Given the pattern you are seeing, I'm wondering if some Open MPI collective call is not finishing until you re-enter the MPI progression engine. Specifically, is

[OMPI users] Help configuring openmpi

2008-05-12 Thread Juan Carlos Larroya Huguet
Hi, I'm using Openmpi in a linux cluster (itanium 64, intel compilers, 8 processors (4 dual) by node) in which openmpi is not the default ( I mean supported) MPI-II implementation. Openmpi has been installed easily on the cluster but I think there is a problem with the configuration. I'm usi