<div>I build up petsc successfully as follows</div>
<div>./configure --with-cc= --prefix=/home/david/petscdir --with-cc=gcc --with-cxx=g++ --with-fc=ifort --download-mpich=1 --download-hypre=1</div>
<div>make</div>
<div>make install</div>
<div>make test</div>
<div> </div>
<div>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.</div>
<div> </div>
<div>David</div>
<div><br><br> </div>
<div class="gmail_quote">On Mon, Mar 22, 2010 at 4:45 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="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">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>
<div>
<div></div>
<div class="h5"><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 --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>> wrote:<br>><br>> > On Mon, Mar 22, 2010 at 3:54 PM, David sheehan <<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 such<br>> >> g77,gcc<br>> >> and g++. Since my application code works very well with ifort, can I 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 GNU<br>> > somehow). You<br>> > jsut provide these compilers to the configure, and use --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>> wrote:<br>
> >><br>> >>> If you have installation issues - send the relavent logs [in this case<br>> >>> configure.log] to petsc-maint.<br>> >>><br>> >>> Here you appear to try too many things.. But its not clear if you are<br>
> >>> installing openmpi/lam yourself - or using default from Red Hat 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 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 allocation<br>> >>> in<br>> >>> > the code,<br>> >>> > so I have to use Intel FORTRAN(ifort) as the compiler to link PETSC<br>
> >>> with my<br>> >>> > application<br>> >>> > code. I can build up PETSC(petsc-3.0.0-p11) plus hypre with Lam MPI but<br>> >>> > without ifort<br>> >>> > successfully. However I can not use ifort to link the PETSC with my<br>
> >>> > application success-<br>> >>> > fully. The link always shows erros about "undefined reference" to 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 which their<br>> > experiments lead.<br>
> > -- Norbert Wiener<br>> ><br>><br><br></div></div></blockquote></div><br>