<html>
<head>
<style><!--
.hmmessage P
{
margin:0px;
padding:0px
}
body.hmmessage
{
font-size: 12pt;
font-family:Calibri
}
--></style></head>
<body class='hmmessage'><div dir='ltr'>Dear Rajeev,<br><br> Thanks for your reply. I now realize mpich is under /opt/local/include/mpich-mp.<br>There is another under /usr/local/include that has an mpif.h with include "mpif-common.h".<br>These are by Indiana University/Stuttgart/UC/Cisco.<br><br> mpif90 -I/opt/local/include/mpich-mp -o tst tst.f (containing include "mpif.h" in tst.f)<br> mpirun -np 2 ./tst<br><br> gives a runtime error <br><br> 1275069467 1275069468 1275070495 (=MPI_INTEGER,MPI_REAL,MPI_DOUBLE_PRECISION)<br> 1275069467 1275069468 1275070495<br> *** An error occurred in MPI_Comm_rank<br> *** reported by process [140735101665281,140733193388032]<br> *** on communicator MPI_COMM_WORLD<br> *** MPI_ERR_COMM: invalid communicator<br> *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,<br> *** and potentially your MPI job)<br>(same for 2nd process)<br><br> Clearly, there I have an initialization error on the basic mpi variables. Is there a possible mix-up <br>between these two mpi packages?<br><br>Best,<br><br>Henry <br><br><div>> From: thakur@mcs.anl.gov<br>> To: discuss@mpich.org<br>> Date: Wed, 16 Jul 2014 09:11:12 +0000<br>> Subject: Re: [mpich-discuss] ifort/mpich installation Mac 10.8.5<br>> <br>> What is mpif-common.h? You need to include mpif.h and provide the path to the mpich include directory. The problem you are seeing is caused because the wrong mpif.h is being picked up.<br>> <br>> Rajeev<br>> <br>> <br>> On Jul 16, 2014, at 2:45 AM, maurice van putten <mvputten2002@hotmail.com> wrote:<br>> <br>> > Hi,<br>> > <br>> > Perhaps someone can provide a solution to what seems to be<br>> > a problem with installation of mpich.<br>> > <br>> > I installed ifort (intel) and mpich (via port install), compile<br>> > a basic test program mpif90 -I/usr/local/include -o tst tst.f <br>> > (here "I/usr/local/include" is included to find mpif-common.h), <br>> > <br>> > PROGRAM mpitest<br>> > integer ierr,my_rank,nm_prcs<br>> > include "mpif-common.h"<br>> > call MPI_INIT(ierr) <br>> > write(*,*)MPI_INTEGER,MPI_REAL,MPI_DOUBLE_PRECISION<br>> > call MPI_COMM_RANK(MPI_COMM_WORLD,my_rank,ierr)<br>> > call MPI_COMM_SIZE(MPI_COMM_WORLD,nm_prcs,ierr)<br>> > write(*,*)'MPI:',my_rank,nm_prcs,ierr<br>> > call MPI_FINALIZE(ierr)<br>> > end<br>> > <br>> > and do mpirun -np 2 ./tst. The result is<br>> > <br>> > 7 13 17<br>> > MPI: 0 1 0<br>> > 7 13 17<br>> > MPI: 0 1 0<br>> > <br>> > It shows that nm_prcs = 1 and both processes show the same my_rank = 0,<br>> > even though ierr =0. <br>> > <br>> > The initialization in mpirun seem to fail, to assign a proper process count 2.<br>> > <br>> > Any ideas on what's amiss?<br>> > <br>> > Many thanks,<br>> > <br>> > Henry.<br>> > _______________________________________________<br>> > discuss mailing list discuss@mpich.org<br>> > To manage subscription options or unsubscribe:<br>> > https://lists.mpich.org/mailman/listinfo/discuss<br>> <br>> _______________________________________________<br>> discuss mailing list discuss@mpich.org<br>> To manage subscription options or unsubscribe:<br>> https://lists.mpich.org/mailman/listinfo/discuss<br></div> </div></body>
</html>