[OMPI users] Starting on remote nodes

We currently use MPICH on our Linux clusters, but due to a high frequency of semaphore problems we are planning to replace it. OpenMPI looks like our best candidate but we have hit a snag. We support multiple compilers (specifically PGI and Intel) and due to incompatibilities in different vendors

Re: [OMPI users] Starting on remote nodes

Hello dear Katherine, On Wednesday 25 October 2006 17:43, Katherine Holcomb wrote: > We currently use MPICH on our Linux clusters, but due to a high > frequency of semaphore problems we are planning to replace it. OpenMPI > looks like our best candidate but we have hit a snag. We support > multip

Re: [OMPI users] Starting on remote nodes

On Oct 25, 2006, at 11:43 AM, Katherine Holcomb wrote: ...We support multiple compilers (specifically PGI and Intel) and due to incompatibilities in different vendors' f90 .mod files, we have separate directories for OpenMPI with each compiler. Therefore we cannot set a global path to the O

Re: [OMPI users] Starting on remote nodes

On Oct 25, 2006, at 11:43 AM, Katherine Holcomb wrote: ...We support multiple compilers (specifically PGI and Intel) and due to incompatibilities in different vendors' f90 .mod files, we have separate directories for OpenMPI with each compiler. Therefore we cannot set a global path to the O

Re: [OMPI users] Starting on remote nodes

> > I presume you left some critical piece of information out of your > message, like the name and configuration of the batch queueing system > you are using. We're using PBS Pro although I don't think it's a factor in this particular situation. (I did find some behavior with PBS Pro that s

[OMPI users] MPI_REDUCE vs. MPI_IN_PLACE vs. F90 Interfaces

Yet another forgotten issue regarding the f90 large interfaces (note that MPI_IN_PLACE is currently an integer, for a time it was a double complex but that has been fixed). Problem I have now is that my patches which worked with 1.2 don't work