None of the C or C++ examples run.  For example, the hello_c.c example in the 
examples directory included with openmpi.  It compiles, but hangs on MPI_Init().

Are your compiler versions different from the ones I’m showing? Apple LLVM 
version 5.0 (clang-500.2.79) (based on LLVM 3.3svn)

Karl


On Nov 27, 2013, at 11:51 AM, Nathan Hjelm <hje...@lanl.gov> wrote:

> Been running on Mavericks all summer with no issues. I do not use the C++ 
> interface
> though (C++ bindings were removed from the MPI standard in 3.0.) Can you try 
> a C
> example and see if that works?
>
> -Nathan Hjelm
> Application Readiness, HPC-5, LANL
>
> On Wed, Nov 27, 2013 at 11:43:05AM -0500, Meredith, Karl wrot
>> Okay, in order to try and track down this problem I have done a fresh 
>> install of OpenMPI-1.7.3 on Mac OS 10.9 (Mavericks).  I am using the Apple 
>> compilers, and not using anything from macports.  The code compiles fine, 
>> but when running the examples for openmpi-1.7.3, the code hangs in 
>> MPI::Init() and never returns.  No error message.  No warning.  It just 
>> hangs.  If I compile in debug mode and do a stack trace, it shows that it is 
>> stalled inside of MPI::Init() every time.  Has anyone been able to 
>> successfully get openmpi working on 10.9?  If so, what, if anything, are you 
>> doing differently?
>>
>> This is how I installed openmpi:
>> ./configure --prefix=$HOME/tools/openmpi-1.7.3
>> make
>> make install
>>
>> Here are my settings, environment variables, compilers, etc:
>>
>> bash-4.2$ which g++
>> /usr/bin/g++
>>
>> bash-4.2$ which gcc
>> /usr/bin/gcc
>>
>> bash-4.2$ which clang
>> /usr/bin/clang
>>
>> bash-4.2$ g++ --version
>> Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr 
>> --with-gxx-include-dir=/usr/include/c++/4.2.1
>> Apple LLVM version 5.0 (clang-500.2.79) (based on LLVM 3.3svn)
>> Target: x86_64-apple-darwin13.0.0
>> Thread model: posix
>>
>> bash-4.2$ gcc --version
>> Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr 
>> --with-gxx-include-dir=/usr/include/c++/4.2.1
>> Apple LLVM version 5.0 (clang-500.2.79) (based on LLVM 3.3svn)
>> Target: x86_64-apple-darwin13.0.0
>> Thread model: posix
>>
>> bash-4.2$ which mpicc
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/bin/mpicc
>>
>> bash-4.2$ which mpic++
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/bin/mpic++
>>
>> bash-4.2$ which mpirun
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/bin/mpirun
>>
>> bash-4.2$ mpicc -show
>> gcc -I/Users/meredithk/tools/openmpi-1.7.3-noenv/include 
>> -L/Users/meredithk/tools/openmpi-1.7.3-noenv/lib -lmpi
>>
>> bash-4.2$ mpic++ -show
>> g++ -I/Users/meredithk/tools/openmpi-1.7.3-noenv/include 
>> -L/Users/meredithk/tools/openmpi-1.7.3-noenv/lib -lmpi_cxx -lmpi
>>
>> bash-4.2$ pwd
>> /Users/meredithk/tools/openmpi-1.7.3-src
>>
>> bash-4.2$ otool -L hello_cxx
>> hello_cxx:
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi_cxx.1.dylib 
>> (compatibility version 3.0.0, current version 3.3.0)
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi.1.dylib (compatibility 
>> version 4.0.0, current version 4.0.0)
>> /usr/lib/libc++.1.dylib (compatibility version 1.0.0, current version 
>> 120.0.0)
>> /usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 
>> 1197.1.1)
>>
>> bash-4.2$ mpirun -n 5 hostname
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com>
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com>
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com>
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com>
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com>
>>
>> bash-4.2$ echo $PATH
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/bin:/usr/bin:/bin:/usr/sbin:/sbin
>>
>> bash-4.2$ echo $LD_LIBRARY_PATH
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib:
>>
>> bash-4.2$ echo $DYLD_LIBRARY_PATH
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib:
>>
>> bash-4.2$ ls /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/
>> libmca_common_sm.4.dylib libmpi_cxx.1.dylib libopen-pal.6.dylib 
>> libopen-trace-format.1.dylib libotfaux.dylib libvt-mpi-unify.0.dylib 
>> libvt-mpi.dylib libvt.0.dylib
>> libmca_common_sm.dylib libmpi_cxx.dylib libopen-pal.dylib 
>> libopen-trace-format.a libotfaux.la libvt-mpi-unify.a libvt-mpi.la libvt.a
>> libmca_common_sm.la libmpi_cxx.la libopen-pal.la libopen-trace-format.dylib 
>> libvt-hyb.0.dylib libvt-mpi-unify.dylib libvt-mt.0.dylib libvt.dylib
>> libmpi.1.dylib libompitrace.0.dylib libopen-rte.6.dylib 
>> libopen-trace-format.la libvt-hyb.a libvt-mpi-unify.la libvt-mt.a libvt.la
>> libmpi.dylib libompitrace.dylib libopen-rte.dylib libotfaux.0.dylib 
>> libvt-hyb.dylib libvt-mpi.0.dylib libvt-mt.dylib openmpi
>> libmpi.la libompitrace.la libopen-rte.la libotfaux.a libvt-hyb.la 
>> libvt-mpi.a libvt-mt.la pkgconfig
>>
>> bash-4.2$ otool -L 
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi_cxx.dylib
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi_cxx.dylib:
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi_cxx.1.dylib 
>> (compatibility version 3.0.0, current version 3.3.0)
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libmpi.1.dylib (compatibility 
>> version 4.0.0, current version 4.0.0)
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libopen-rte.6.dylib 
>> (compatibility version 7.0.0, current version 7.0.0)
>> /Users/meredithk/tools/openmpi-1.7.3-noenv/lib/libopen-pal.6.dylib 
>> (compatibility version 7.0.0, current version 7.0.0)
>> /usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 
>> 1197.1.1)
>> /usr/lib/libc++.1.dylib (compatibility version 1.0.0, current version 
>> 120.0.0)
>>
>> On Nov 27, 2013, at 9:41 AM, Meredith, Karl 
>> <karl.mered...@fmglobal.com<mailto:karl.mered...@fmglobal.com>> wrote:
>>
>> I’m pretty sure it is using the correct g++
>>
>> $ )which g++
>> /opt/local/bin/g++
>>
>>
>> $ )echo $PATH
>> /Users/meredithk/tools/openmpi/bin:/opt/local/bin:/opt/local/sbin:/Users/meredithk/tools/bin:/Users/meredithk/OpenFOAM/fireFoam-2.2.x/scripts:/Users/meredithk/OpenFOAM/ThirdParty-2.2.x/platforms/darwinIntel64Gcc46/gperftools-svn/bin:/Applications/paraview.app/Contents/bin:/Users/meredithk/OpenFOAM/ThirdParty-2.2.x/platforms/darwinIntel64Gcc46/paraview-3.12.0/bin:/Users/meredithk/OpenFOAM/meredithk-2.2.x/platforms/darwinIntel64Gcc46DPOpt/bin:/Users/meredithk/OpenFOAM/site/2.2.x/platforms/darwinIntel64Gcc46DPOpt/bin:/Users/meredithk/OpenFOAM/OpenFOAM-2.2.x/platforms/darwinIntel64Gcc46DPOpt/bin:/Users/meredithk/OpenFOAM/OpenFOAM-2.2.x/bin:/Users/meredithk/OpenFOAM/OpenFOAM-2.2.x/wmake:/Developer/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin
>>
>>
>> $ )g++ --version
>> g++ (MacPorts gcc46 4.6.4_3) 4.6.4
>>
>>
>> Karl
>>
>>
>>
>> On Nov 27, 2013, at 3:23 AM, Iliev, Hristo 
>> <il...@rz.rwth-aachen.de<mailto:il...@rz.rwth-aachen.de><mailto:il...@rz.rwth-aachen.de>>
>>  wrote:
>>
>> Karl,
>>
>> The Xcode command-line tools provide a g++ command that is effectively
>> clang++. Since mpic++ invokes g++ without the full path to it, it might pick
>> the wrong g++. Make sure that /opt/local/bin is the first item in your
>> $PATH.
>>
>> Hristo
>>
>> --
>> Hristo Iliev, PhD - High Performance Computing Team / JARA-HPC
>> RWTH Aachen University, Center for Computing and Communication
>> Rechen- und Kommunikationszentrum der RWTH Aachen
>> Seffenter Weg 23, D-52074 Aachen (Germany)
>>
>> -----Original Message-----
>> From: users [mailto:users-boun...@open-mpi.org] On Behalf Of Meredith,
>> Karl
>> Sent: Tuesday, November 26, 2013 9:33 PM
>> To: Open MPI Users
>> Subject: Re: [OMPI users] open-mpi on Mac OS 10.9 (Mavericks)
>>
>> Here are the results of those two commands:
>>
>> $ )mpic++ -show
>> g++ -I/Users/meredithk/tools/openmpi/include -
>> L/Users/meredithk/tools/openmpi/lib -lmpi_cxx -lmpi -lm
>>
>> $ )otool -L /Users/meredithk/tools/openmpi/lib/libmpi_cxx.dylib
>> /Users/meredithk/tools/openmpi/lib/libmpi_cxx.dylib:
>> /Users/meredithk/tools/openmpi/lib/libmpi_cxx.1.dylib
>> (compatibility version 2.0.0, current version 2.2.0)
>> /Users/meredithk/tools/openmpi/lib/libmpi.1.dylib (compatibility
>> version 2.0.0, current version 2.8.0)
>> /opt/local/lib/libgcc/libstdc++.6.dylib (compatibility version
>> 7.0.0,
>> current version 7.18.0)
>> /usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current
>> version
>> 1197.1.1)
>> /opt/local/lib/libgcc/libgcc_s.1.dylib (compatibility version 1.0.0,
>> current version 1.0.0)
>>
>> It looks like libstdc++ is being used and g++ is being used.
>>
>> Karl
>>
>>
>> On Nov 25, 2013, at 6:56 PM, Pierre Jolivet 
>> <joli...@ann.jussieu.fr<mailto:joli...@ann.jussieu.fr><mailto:joli...@ann.jussieu.fr>>
>> wrote:
>>
>> Karl,
>> What does "mpic++ -show" returns ? It is possible that you are
>> compiling/linking with "c++", which will defaults to clang++, while you
>> compiled OpenMPI with g++.
>> Since libstdc++ and libc++ have incompatible ABI, that might be why you
>> are getting a wrong behavior.
>> Also, it could be worthwhile to have a look at "otool -L
>> /Users/meredithk/tools/openmpi/lib/libmpi_cxx.dylib"
>> Pierre
>>
>> On Nov 25, 2013, at 7:38 AM, Meredith, Karl
>> <karl.mered...@fmglobal.com<mailto:karl.mered...@fmglobal.com><mailto:karl.mered...@fmglobal.com>>
>>  wrote:
>>
>> I do have DYLD_LIBRARY_PATH set as well, and I get the same problem:
>>
>> DYLD_LIBRARY_PATH=/Users/meredithk/tools/openmpi/lib
>>
>> Here's the directory listing of /Users/meredithk/tools/openmpi/lib
>>
>> $ )ls -1
>> libmca_common_sm.3.dylib*
>> libmca_common_sm.dylib@
>> libmca_common_sm.la*
>> libmpi.1.dylib*
>> libmpi.dylib@
>> libmpi.la*
>> libmpi_cxx.1.dylib*
>> libmpi_cxx.dylib@
>> libmpi_cxx.la*
>> libmpi_f77.1.dylib*
>> libmpi_f77.dylib@
>> libmpi_f77.la*
>> libmpi_f90.a
>> libmpi_f90.la*
>> libompitrace.0.dylib*
>> libompitrace.dylib@
>> libompitrace.la*
>> libopen-pal.4.dylib*
>> libopen-pal.dylib@
>> libopen-pal.la*
>> libopen-rte.4.dylib*
>> libopen-rte.dylib@
>> libopen-rte.la*
>> libopen-trace-format.1.dylib*
>> libopen-trace-format.a
>> libopen-trace-format.dylib@
>> libopen-trace-format.la*
>> libotfaux.0.dylib*
>> libotfaux.a
>> libotfaux.dylib@
>> libotfaux.la*
>> libvt-hyb.0.dylib*
>> libvt-hyb.a
>> libvt-hyb.dylib@
>> libvt-hyb.la*
>> libvt-mpi-unify.0.dylib*
>> libvt-mpi-unify.a
>> libvt-mpi-unify.dylib@
>> libvt-mpi-unify.la*
>> libvt-mpi.0.dylib*
>> libvt-mpi.a
>> libvt-mpi.dylib@
>> libvt-mpi.la*
>> libvt-mt.0.dylib*
>> libvt-mt.a
>> libvt-mt.dylib@
>> libvt-mt.la*
>> libvt-pomp.a
>> libvt-pomp.la*
>> libvt.0.dylib*
>> libvt.a
>> libvt.dylib@
>> libvt.la*
>> mpi.mod*
>> openmpi/
>> pkgconfig/
>>
>>
>> I don't notice anything out of ordinary.
>>
>> Karl
>>
>>
>> On Nov 25, 2013, at 8:31 AM, Reuti 
>> <re...@staff.uni-marburg.de<mailto:re...@staff.uni-marburg.de><mailto:re...@staff.uni-marburg.de>>
>>  wrote:
>>
>> Am 25.11.2013 um 14:25 schrieb Meredith, Karl:
>>
>> I do have these two environment variables set:
>>
>> LD_LIBRARY_PATH=/Users/meredithk/tools/openmpi/lib
>>
>> On a Mac it should DYLD_LIBRARY_PATH - and there are *.dylib files in
>> your /Users/meredithk/tools/openmpi/lib?
>>
>> -- Reuti
>>
>>
>> PATH=/Users/meredithk/tools/openmpi/bin
>>
>> Running mpirun seems to work fine with a simple command, like
>> hostname:
>>
>> $ )mpirun -n 2 hostname
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com/><http://meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com/>>
>> meredithk-mac.corp.fmglobal.com<http://meredithk-mac.corp.fmglobal.com/>
>>
>> I am trying to run the simple hello_cxx example from the openmpi
>> distribution, compiled as such:
>> mpic++ -g    hello_cxx.cc   -o hello_cxx
>>
>> It compiles fine, without warning or error.  However, when I go to
>> run
>> the example, it stalls on the MPI::Init() command:
>> mpirun -np 1 hello_cxx
>> It never errors out or crashes.  It simply hangs.
>>
>> I am using the same mpic++ and mpirun version:
>> $ )which mpirun
>> /Users/meredithk/tools/openmpi/bin/mpirun
>>
>> $ )which mpic++
>> /Users/meredithk/tools/openmpi/bin/mpic++
>>
>> Not quite sure what else to check.
>>
>> Karl
>>
>>
>> On Nov 23, 2013, at 5:29 PM, Ralph Castain 
>> <r...@open-mpi.org<mailto:r...@open-mpi.org><mailto:r...@open-mpi.org>>
>> wrote:
>>
>> Strange - I run on Mavericks now without problem. Can you run
>> "mpirun -n 1 hostname"?
>>
>> You also might want to check your PATH and LD_LIBRARY_PATH to
>> ensure you have the prefix where you installed OMPI 1.6.5 at the front.
>> Mac
>> distributes a very old version of OMPI with its software and you don't
>> want
>> to pick it up by mistake.
>>
>>
>> On Nov 22, 2013, at 1:45 PM, Meredith, Karl
>> <karl.mered...@fmglobal.com<mailto:karl.mered...@fmglobal.com><mailto:karl.mered...@fmglobal.com>>
>>  wrote:
>>
>> I recently upgraded my 2013 Macbook Pro (Retina display) from 10.8
>> to 10.9.  I downloaded and installed openmpi-1.6.5 and compiled it with
>> gcc
>> 4.8 (gcc installed from macports).
>> openmpi compiled and installed without error.
>>
>> However, when I try to run any of the example test cases, the code
>> gets stuck inside the first MPI::Init() call and never returns.
>>
>> Any thoughts on what might be going wrong?
>>
>> The same install on OS 10.8 works fine and the example test cases
>> run without error.
>>
>> Karl
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>> <smime.p7s>_______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org><mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org<mailto:us...@open-mpi.org>
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> us...@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
> <ATT00001>_______________________________________________
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users

Reply via email to