I was able to build OMPI (1.1a9r10177) with nag f95 5.0(414) with out any problems. To configure it be sure to use: FCFLAGS='-mismatch -w' That is the only really big change, I did use a prefix path to pbs (for tm) I also use portland for both my c and c++ compiler. Here if my full configure, its mostlikly useless to you, but somthing will make sence to you:

./configure --prefix=/home/software/rhel4/openmpi-1.1a8-nag --with- tm=/home/software/torque-2.0.0p8/ FC=/afs/engin.umich.edu/caen/rhel_4/ nag/bin/f95 F77=/afs/engin.umich.edu/caen/rhel_4/nag/bin/f95 FCFLAGS="-mismatch -w" CC=pgcc CXX=pgCC

Some things i found, you cant have FCFLAGS have -O3 your mpif90 will segfault.

Currently though we have problems with OMPI with nag though. So if some devs have some in sight into this problem would be help. Heres the problem, the package builds fine, on execution the following error is given:

-bash-3.00$ mpirun -np 2 SWMF.exe
[nyx-login.engin.umich.edu:06116] *** An error occurred in MPI_Comm_rank
[nyx-login.engin.umich.edu:06116] *** on communicator MPI_COMM_WORLD
[nyx-login.engin.umich.edu:06116] *** MPI_ERR_COMM: invalid communicator
[nyx-login.engin.umich.edu:06116] *** MPI_ERRORS_ARE_FATAL (goodbye)
1 additional process aborted (not shown)

I know there were some similar messages on the list sooner, Is this a known problem? If so is a fix in the works? And last is there a timeline for such a fix?
Brock


On Jun 2, 2006, at 2:32 PM, Doug Roberts wrote:


Hello, I have tried openmpi-1.1a9r10177 and make is still crashing at
the same point, although the error message has change as shown in the
next snippet. I've attached the config.log, config.out and make.out

make[4]: Entering directory
`/opt/openmpi/openmpi-1.1a9r10177.bld/ompi/mpi/f90'
./scripts/mpi-f90-interfaces.h.sh /opt/openmpi/ openmpi-1.1a9r10177.bld/ompi/mpi/f90 > mpi-f90-interfaces.h
***************************************************************
* Compiling the mpi.f90 file may take a few minutes.
* This is quite normal -- do not be alarmed if the compile
* process seems to 'hang' at this point for several minutes.
***************************************************************
f95 -I../../../ompi/include -I../../../ompi/include -I. -I.  -c -I. -o
mpi.o mpi.f90
Extension: mpi.f90: DOUBLE COMPLEX keyword
Extension: mpi-f90-interfaces.h, line 1512: Byte count on numeric data type
           detected at *@1
Extension: mpi-f90-interfaces.h, line 1519: Byte count on numeric data type
           detected at *@2
Extension: mpi-f90-interfaces.h, line 1526: Byte count on numeric data type
           detected at *@4
Extension: mpi-f90-interfaces.h, line 1533: Byte count on numeric data type
           detected at *@8
Extension: mpi-f90-interfaces.h, line 1540: Byte count on numeric data type
           detected at *@4
Extension: mpi-f90-interfaces.h, line 1547: Byte count on numeric data type
           detected at *@8
Many thanks,
-Doug


---------- Forwarded message ----------
From: Jeff Squyres \(jsquyres\) (jsquyres_at_[hidden])
Date: 2006-06-01 17:37:36

This was actually reported earlier today (off list). It was the result of a botched merge from the trunk to the v1.1 branch. I have fixed the issue as of r10171 (it was a one-line mistake); the fix should show up
in the snapshot tarballs tonight.


---------- Forwarded message ----------
Date: Thu, 1 Jun 2006 16:45:50 -0400 (EDT)
From: Doug Roberts <robe...@sharcnet.ca>
To: us...@open-mpi.org
Subject: openmpi-1.1a9r10157 Fails to build with Nag f95 Compiler

Hi, I'm using the NAGWare Fortran 95 compiler Release 5.0(414), but make
fails as shown in the snippet below.  I've attached the config.log,
config.out and make.out files. The system is a dual processor Opteron
server running a 2.6 x86_64 linux kernel and has a myrinet mx based
interconnect which i define at configure time.

make[4]: Entering directory
`/opt/openmpi/openmpi-1.1a9r10157.bld/ompi/mpi/f90'
./scripts/mpi-f90-interfaces.h.sh
/opt/openmpi/openmpi-1.1a9r10157.bld/ompi/mpi/f90 > mpi-f90- interfaces.h
***************************************************************
* Compiling the mpi.f90 file may take a few minutes.
* This is quite normal -- do not be alarmed if the compile
* process seems to 'hang' at this point for several minutes.
***************************************************************
f95 -I../../../ompi/include -I../../../ompi/include -I. -I.  -c -I. -o
mpi.o  mpi.f90
Extension: mpi.f90: DOUBLE COMPLEX keyword
Error: attr_fn-f90-interfaces.h, line 21: MPI_TYPE_NULL_DELETE_FN has
already been declared EXTERNAL
       detected at SUBROUTINE@MPI_TYPE_NULL_DELETE_FN
Warning: attr_fn-f90-interfaces.h, line 24: Unused dummy argument TYPE
         detected at MPI_TYPE_NULL_DELETE_FN@<end-of-statement>
Warning: attr_fn-f90-interfaces.h, line 24: Unused dummy argument IERR
         detected at MPI_TYPE_NULL_DELETE_FN@<end-of-statement>
Warning: attr_fn-f90-interfaces.h, line 24: Unused dummy argument
EXTRA_STATE
         detected at MPI_TYPE_NULL_DELETE_FN@<end-of-statement>
Warning: attr_fn-f90-interfaces.h, line 24: Unused dummy argument
ATTRIBUTE_VAL_OUT
         detected at MPI_TYPE_NULL_DELETE_FN@<end-of-statement>
Warning: attr_fn-f90-interfaces.h, line 24: Unused dummy argument
TYPE_KEYVAL
         detected at MPI_TYPE_NULL_DELETE_FN@<end-of-statement>
Error: attr_fn-f90-interfaces.h, line 26: MPI_TYPE_NULL_COPY_FN has
already been declared EXTERNAL
       detected at SUBROUTINE@MPI_TYPE_NULL_COPY_FN

Any help greatly appreciated,
-Doug
<ompi-output.tar.gz>
_______________________________________________
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users

Reply via email to