Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

From: Andrus, Mr. Brian \(Contractor\) (brian.andrus_at_[hidden])
Date: 2006-12-20 12:05:03

I am trying to build an OpenMPI rpm for RHEL4U4 using the following:

rpmbuild --rebuild --define configure_options"CC=pgcc CXX=pgCC F77=pgf77
FC=pgf90 FFLAGS=-fastsse FCFLAGS=-fastsse" ./openmpi-1.1.1-1.src.rpm

It builds the rpm but there are some warnings:
configure: WARNING: -fno-strict-aliasing has been added to CFLAGS
configure: WARNING: -finline-functions has been added to CXXFLAGS
configure: WARNING: *** Fortran 77 and Fortran 90 compilers are not link
configure: WARNING: *** Disabling MPI Fortran 90/95 bindings
configure: WARNING: Unknown architecture ... proceeding anyway
configure: WARNING: File locks may not work with NFS. See the
Installation and
users manual for instructions on testing and if necessary fixing this

And when I try to compile a simple hello world fortran program:

[root_at_system ~]# mpif90 hello.f

Unfortunately, this installation of Open MPI was not compiled with
Fortran 90 support.  As such, the mpif90 compiler is non-functional.
I have PGI v6.1 compilers installed at /usr/pgi/linux86-64/6.1/
Brian Andrus
QSS Group, Inc.
Naval Research Laboratory
Monterey, California
Desk: 831-656-4839
-----Original Message-----
From: users-bounces_at_[hidden] [mailto:users-bounces_at_[hidden]] On
Behalf Of Renato Golin
Sent: Wednesday, December 20, 2006 7:48 AM
To: Open MPI Users
Subject: Re: [OMPI users] Suggestions needed for parallelisation of
sortingalgorithms (quicksort)
On 12/20/06, Harakiri <harakiri_23_at_[hidden]> wrote:
> I will study through the suggested paper, however i actually read a 
> different paper which suggested using less messages, i would imagine 
> that for arrays of numbers lets say 100 Millions - the network 
> messages become the critical factor.
It depends completely on your network topology and technology (ie.
bandwidth and latency). It's very hard to predict a generic behaviour
other than: "more data is worse".
Ethernet is quite good at bandwidth but not at latency so a few big
chunks are better than lots of small chunks but it also depends how the
network is carrying your packages along the way.
The network is a critical factor only if it's running time is comparable
or greater than the processing time. Copying 1Mb between nodes is
critical for a nanosecond computation but not if it'll take days.
Reclaim your digital rights, eliminate DRM, learn more at
users mailing list