[petsc-dev] PETSC's compilation

[David sheehan]

The "bin" directory has the following files:

adiforfix.py           mpich2version     mpiexec.poe
parkill                        taucc.py
adprocess.py       mpicxx               mpiexec.prun
parseargs.py             TOPSGenerator.py
chibaoutput          mpiexec             mpiexec.sshsync
petsc_libtool              TOPSInstaller.py
configVars.py       mpiexec.chiba    mpiexec.uni
petscmpiexec             update.py
hostnames.chiba  mpiexec.gmalloc mpiexec.valgrind
popup                         urlget
matlab                  mpiexec.lam      mpif77
portabilitycheck.py      urlget.py
mpicc                   mpiexec.llrun      mpif90
processSummary.py    win32fe
which one is "mpirun"? thanks.

David

On Mon, Mar 22, 2010 at 5:44 PM, Satish Balay <balay at mcs.anl.gov> wrote:

>
> You should look for mpiexec. It will be in the 'bin' dir for the
> prefix used - i.ed /home/david/petscdir/bin/mpiexec
>
> Satish
>
>
> On Mon, 22 Mar 2010, David sheehan wrote:
>
> > I build up petsc successfully as follows
> > ./configure --with-cc= --prefix=/home/david/petscdir --with-cc=gcc
> > --with-cxx=g++ --with-fc=ifort --download-mpich=1 --download-hypre=1
> > make
> > make install
> > make test
> >
> > Also, I can link it with my application. Now I need to run my application
> > with the petsc, where can I find "mpirun" for the mpich downloaded to run
> my
> > application? thanks.
> >
> > David
> >
> >
> >
> > On Mon, Mar 22, 2010 at 4:45 PM, Satish Balay <balay at mcs.anl.gov> wrote:
> >
> > > You can't use 2 MPIs at same time. i.e use either --download-mpich=1
> > > or --download-openmpi=1 - but not both.
> > >
> > > Satish
> > >
> > > On Mon, 22 Mar 2010, David sheehan wrote:
> > >
> > > > You mean,
> > > > ./configure --with-cc=gcc --with-cxx=g++ --with-fc=ifort
> > > --download-mpich=1
> > > >  --download-hypre=1 --download-openmpi=1
> > > > thanks.
> > > >
> > > > David
> > > >
> > > > On Mon, Mar 22, 2010 at 3:58 PM, Matthew Knepley <knepley at gmail.com>
> > > wrote:
> > > >
> > > > > On Mon, Mar 22, 2010 at 3:54 PM, David sheehan <
> > > david.sheehanjr at gmail.com>wrote:
> > > > >
> > > > >> I don't have icc and icpc. I only have ifort and gnu compilers
> such
> > > > >> g77,gcc
> > > > >> and g++. Since my application code works very well with ifort, can
> I
> > > build
> > > > >>
> > > > >> up PETSC plus Hypre with ifort and gnu compilers? thanks.
> > > > >>
> > > > >
> > > > > It might be possible (though not guaranteed if ifort conflicts with
> GNU
> > > > > somehow). You
> > > > > jsut provide these compilers to the configure, and use
> > > --download-openmpi.
> > > > >
> > > > >    Matt
> > > > >
> > > > >
> > > > >>
> > > > >> David
> > > > >>
> > > > >> On Mon, Mar 22, 2010 at 3:29 PM, Satish Balay <balay at mcs.anl.gov>
> > > wrote:
> > > > >>
> > > > >>> If you have installation issues - send the relavent logs [in this
> > > case
> > > > >>> configure.log] to petsc-maint.
> > > > >>>
> > > > >>> Here you appear to try too many things.. But its not clear if you
> are
> > > > >>> installing openmpi/lam yourself - or using default from Red Hat
> 3.4.
> > > > >>> [note - default openmpi will be built with gnu compilers - so
> > > > >>> unuseable from ifort].
> > > > >>>
> > > > >>> Thing to do:
> > > > >>>
> > > > >>> - decide on compilers you want to use.
> > > > >>> - build PETSc and mpi with these compilers
> > > > >>>
> > > > >>> [for eg: configure CC=icc CXX=icpc FC=ifort --download-mpich=1
> > > > >>> --download-hypre=1]
> > > > >>>
> > > > >>> Note: alternative f90 compilers seable on linux are gfortran, g95
> > > > >>>
> > > > >>> Satish
> > > > >>>
> > > > >>> On Mon, 22 Mar 2010, David sheehan wrote:
> > > > >>>
> > > > >>> > Hi,
> > > > >>> > I am trying to compile the PETSC with hypre. I have Intel
> FORTRAN,
> > > > >>> openmpi
> > > > >>> > and  lam
> > > > >>> > MPI  (gcc version 3.4.6 (Red Hat 3.4.6-3)) available.
> > > > >>> >
> > > > >>> > Since my application code is in FORTRAN with dynamic memory
> > > allocation
> > > > >>> in
> > > > >>> > the code,
> > > > >>> > so I have to use Intel FORTRAN(ifort) as the compiler to link
> PETSC
> > > > >>> with my
> > > > >>> > application
> > > > >>> > code. I can build up PETSC(petsc-3.0.0-p11) plus hypre with Lam
> MPI
> > > but
> > > > >>> > without ifort
> > > > >>> > successfully. However I can not use ifort to link the PETSC
> with my
> > > > >>> > application success-
> > > > >>> > fully. The link always shows erros about "undefined reference"
> to
> > > MPI
> > > > >>> parts
> > > > >>> > in my application
> > > > >>> > code such as 'mpi_send_', 'mpi_recv_', 'mpi_waitany_',
> > > > >>> 'mpi_get_count_',
> > > > >>> > and etc.
> > > > >>> >
> > > > >>> > Can any one help me out? thanks in advance.
> > > > >>> >
> > > > >>> > Best Regards,
> > > > >>> >
> > > > >>> > David
> > > > >>> >
> > > > >>>
> > > > >>>
> > > > >>
> > > > >
> > > > >
> > > > > --
> > > > > What most experimenters take for granted before they begin their
> > > > > experiments is infinitely more interesting than any results to
> which
> > > their
> > > > > experiments lead.
> > > > > -- Norbert Wiener
> > > > >
> > > >
> > >
> > >
> >
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20100322/75bf304a/attachment.html>