AND THIS IS NOT DEV!<div><br></div><div>Take this discussion to <a href="mailto:petsc-maint@mcs.anl.gov">petsc-maint@mcs.anl.gov</a>, and any future discussions</div><div>of this kind, as I suggested before.</div><div><br>
</div><div> Matt<br><div><br><div class="gmail_quote">On Mon, Mar 22, 2010 at 5:58 PM, Satish Balay <span dir="ltr"><<a href="mailto:balay@mcs.anl.gov">balay@mcs.anl.gov</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
As mentioned before - its 'mpiexec'<br>
<div><div></div><div class="h5"><br>
<br>
Satish<br>
<br>
<br>
On Mon, 22 Mar 2010, David sheehan wrote:<br>
<br>
> The "bin" directory has the following files:<br>
><br>
> adiforfix.py mpich2version mpiexec.poe<br>
> parkill taucc.py<br>
> adprocess.py mpicxx mpiexec.prun<br>
> parseargs.py TOPSGenerator.py<br>
> chibaoutput mpiexec mpiexec.sshsync<br>
> petsc_libtool TOPSInstaller.py<br>
> configVars.py mpiexec.chiba mpiexec.uni<br>
> petscmpiexec update.py<br>
> hostnames.chiba mpiexec.gmalloc mpiexec.valgrind<br>
> popup urlget<br>
> matlab mpiexec.lam mpif77<br>
> portabilitycheck.py urlget.py<br>
> mpicc mpiexec.llrun mpif90<br>
> processSummary.py win32fe<br>
> which one is "mpirun"? thanks.<br>
><br>
> David<br>
><br>
> On Mon, Mar 22, 2010 at 5:44 PM, Satish Balay <<a href="mailto:balay@mcs.anl.gov">balay@mcs.anl.gov</a>> wrote:<br>
><br>
> ><br>
> > You should look for mpiexec. It will be in the 'bin' dir for the<br>
> > prefix used - i.ed /home/david/petscdir/bin/mpiexec<br>
> ><br>
> > Satish<br>
> ><br>
> ><br>
> > On Mon, 22 Mar 2010, David sheehan wrote:<br>
> ><br>
> > > I build up petsc successfully as follows<br>
> > > ./configure --with-cc= --prefix=/home/david/petscdir --with-cc=gcc<br>
> > > --with-cxx=g++ --with-fc=ifort --download-mpich=1 --download-hypre=1<br>
> > > make<br>
> > > make install<br>
> > > make test<br>
> > ><br>
> > > Also, I can link it with my application. Now I need to run my application<br>
> > > with the petsc, where can I find "mpirun" for the mpich downloaded to run<br>
> > my<br>
> > > application? thanks.<br>
> > ><br>
> > > David<br>
> > ><br>
> > ><br>
> > ><br>
> > > On Mon, Mar 22, 2010 at 4:45 PM, Satish Balay <<a href="mailto:balay@mcs.anl.gov">balay@mcs.anl.gov</a>> wrote:<br>
> > ><br>
> > > > You can't use 2 MPIs at same time. i.e use either --download-mpich=1<br>
> > > > or --download-openmpi=1 - but not both.<br>
> > > ><br>
> > > > Satish<br>
> > > ><br>
> > > > On Mon, 22 Mar 2010, David sheehan wrote:<br>
> > > ><br>
> > > > > You mean,<br>
> > > > > ./configure --with-cc=gcc --with-cxx=g++ --with-fc=ifort<br>
> > > > --download-mpich=1<br>
> > > > > --download-hypre=1 --download-openmpi=1<br>
> > > > > thanks.<br>
> > > > ><br>
> > > > > David<br>
> > > > ><br>
> > > > > On Mon, Mar 22, 2010 at 3:58 PM, Matthew Knepley <<a href="mailto:knepley@gmail.com">knepley@gmail.com</a>><br>
> > > > wrote:<br>
> > > > ><br>
> > > > > > On Mon, Mar 22, 2010 at 3:54 PM, David sheehan <<br>
> > > > <a href="mailto:david.sheehanjr@gmail.com">david.sheehanjr@gmail.com</a>>wrote:<br>
> > > > > ><br>
> > > > > >> I don't have icc and icpc. I only have ifort and gnu compilers<br>
> > such<br>
> > > > > >> g77,gcc<br>
> > > > > >> and g++. Since my application code works very well with ifort, can<br>
> > I<br>
> > > > build<br>
> > > > > >><br>
> > > > > >> up PETSC plus Hypre with ifort and gnu compilers? thanks.<br>
> > > > > >><br>
> > > > > ><br>
> > > > > > It might be possible (though not guaranteed if ifort conflicts with<br>
> > GNU<br>
> > > > > > somehow). You<br>
> > > > > > jsut provide these compilers to the configure, and use<br>
> > > > --download-openmpi.<br>
> > > > > ><br>
> > > > > > Matt<br>
> > > > > ><br>
> > > > > ><br>
> > > > > >><br>
> > > > > >> David<br>
> > > > > >><br>
> > > > > >> On Mon, Mar 22, 2010 at 3:29 PM, Satish Balay <<a href="mailto:balay@mcs.anl.gov">balay@mcs.anl.gov</a>><br>
> > > > wrote:<br>
> > > > > >><br>
> > > > > >>> If you have installation issues - send the relavent logs [in this<br>
> > > > case<br>
> > > > > >>> configure.log] to petsc-maint.<br>
> > > > > >>><br>
> > > > > >>> Here you appear to try too many things.. But its not clear if you<br>
> > are<br>
> > > > > >>> installing openmpi/lam yourself - or using default from Red Hat<br>
> > 3.4.<br>
> > > > > >>> [note - default openmpi will be built with gnu compilers - so<br>
> > > > > >>> unuseable from ifort].<br>
> > > > > >>><br>
> > > > > >>> Thing to do:<br>
> > > > > >>><br>
> > > > > >>> - decide on compilers you want to use.<br>
> > > > > >>> - build PETSc and mpi with these compilers<br>
> > > > > >>><br>
> > > > > >>> [for eg: configure CC=icc CXX=icpc FC=ifort --download-mpich=1<br>
> > > > > >>> --download-hypre=1]<br>
> > > > > >>><br>
> > > > > >>> Note: alternative f90 compilers seable on linux are gfortran, g95<br>
> > > > > >>><br>
> > > > > >>> Satish<br>
> > > > > >>><br>
> > > > > >>> On Mon, 22 Mar 2010, David sheehan wrote:<br>
> > > > > >>><br>
> > > > > >>> > Hi,<br>
> > > > > >>> > I am trying to compile the PETSC with hypre. I have Intel<br>
> > FORTRAN,<br>
> > > > > >>> openmpi<br>
> > > > > >>> > and lam<br>
> > > > > >>> > MPI (gcc version 3.4.6 (Red Hat 3.4.6-3)) available.<br>
> > > > > >>> ><br>
> > > > > >>> > Since my application code is in FORTRAN with dynamic memory<br>
> > > > allocation<br>
> > > > > >>> in<br>
> > > > > >>> > the code,<br>
> > > > > >>> > so I have to use Intel FORTRAN(ifort) as the compiler to link<br>
> > PETSC<br>
> > > > > >>> with my<br>
> > > > > >>> > application<br>
> > > > > >>> > code. I can build up PETSC(petsc-3.0.0-p11) plus hypre with Lam<br>
> > MPI<br>
> > > > but<br>
> > > > > >>> > without ifort<br>
> > > > > >>> > successfully. However I can not use ifort to link the PETSC<br>
> > with my<br>
> > > > > >>> > application success-<br>
> > > > > >>> > fully. The link always shows erros about "undefined reference"<br>
> > to<br>
> > > > MPI<br>
> > > > > >>> parts<br>
> > > > > >>> > in my application<br>
> > > > > >>> > code such as 'mpi_send_', 'mpi_recv_', 'mpi_waitany_',<br>
> > > > > >>> 'mpi_get_count_',<br>
> > > > > >>> > and etc.<br>
> > > > > >>> ><br>
> > > > > >>> > Can any one help me out? thanks in advance.<br>
> > > > > >>> ><br>
> > > > > >>> > Best Regards,<br>
> > > > > >>> ><br>
> > > > > >>> > David<br>
> > > > > >>> ><br>
> > > > > >>><br>
> > > > > >>><br>
> > > > > >><br>
> > > > > ><br>
> > > > > ><br>
> > > > > > --<br>
> > > > > > What most experimenters take for granted before they begin their<br>
> > > > > > experiments is infinitely more interesting than any results to<br>
> > which<br>
> > > > their<br>
> > > > > > experiments lead.<br>
> > > > > > -- Norbert Wiener<br>
> > > > > ><br>
> > > > ><br>
> > > ><br>
> > > ><br>
> > ><br>
> ><br>
> ><br>
><br>
<br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>
-- Norbert Wiener<br>
</div></div>