Open MPI User's Mailing List Archives

From: Jeremias Spiegel (jeremias.spiegel_at_[hidden])
Date: 2007-10-14 14:38:10

• Next message: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"
• Previous message: Torsten Hoefler: "Re: [OMPI users] Re :Re: Re :Re: Tuning Openmpi with IB Interconnect"
• Next in thread: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"
• Reply: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"

Hi,
I'm working with Open-Mpi on an infiniband-cluster and have some strange
effect when using MPI_Isend(). To my understanding this should always be
quicker than MPI_Send() and MPI_Ssend(), yet in my program both MPI_Send()
and MPI_Ssend() reproducably perform quicker than SSend(). Is there something
obvious I'm missing?

Regards,
Jeremias

• Next message: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"
• Previous message: Torsten Hoefler: "Re: [OMPI users] Re :Re: Re :Re: Tuning Openmpi with IB Interconnect"
• Next in thread: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"
• Reply: George Bosilca: "Re: [OMPI users] Performance of MPI_Isend() worse than MPI_Send() and even MPI_Ssend()"