[OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
Hi,
Following the suggestion by Gilles Gouaillardet (
https://mail-archive.com/users@lists.open-mpi.org/msg29688.html), I ran a
configure command for a program like this

​# ../Src/configure FC=/export/apps/siesta/openmpi-1.8.8/bin/mpifort
--with-blas=libopenblas.a --with-lapack=liblapack.a
--with-scalapack=libscalapack.a
checking build system type... x86_64-unknown-linux-gnu
checking host system type... x86_64-unknown-linux-gnu
checking for Fortran compiler default output file name... a.out
checking whether the Fortran compiler works... configure: error: cannot run
Fortran compiled programs.
If you meant to cross compile, use `--host'.
See `config.log' for more details.



The content of config.log is available at ​http://pastebin.com/LTxxRMwH

It seems that mpifort (the wrapper compiler) has different usage than
previous mpif90

Any idea about that?


Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Gilles Gouaillardet 

Hi,


this is the relevant part of your config.log



configure:1594: checking whether the Fortran compiler works
configure:1600: ./a.out
./a.out: symbol lookup error: 
/export/apps/siesta/openmpi-1.8.8/lib/libmpi_mpifh.so.2: undefined 
symbol: mpi_fortran_weights_empty

configure:1603: $? = 127
configure:1612: error: cannot run Fortran compiled programs.


it seems something is busted with this Open MPI install.

can you please run

nm /export/apps/siesta/openmpi-1.8.8/lib/libmpi_mpifh.so.2 | grep -i 
mpi_fortran_weights_empty
nm /export/apps/siesta/openmpi-1.8.8/lib/libmpi.so.1 | grep -i 
mpi_fortran_weights_empty

ldd /export/apps/siesta/openmpi-1.8.8/lib/libmpi_mpifh.so.2

hopefully we will find out what is going wrong
(i'd like to make sure you are not using IntelMPI libmpi.so.1 with Open 
MPI libmpi_mpifh.so.2, that can happen if Intel MPI appears first in 
your LD_LIBRARY_PATH)


Cheers,

Gilles

On 9/12/2016 3:59 PM, Mahmood Naderan wrote:

Hi,
Following the suggestion by Gilles Gouaillardet 
(https://mail-archive.com/users@lists.open-mpi.org/msg29688.html), I 
ran a configure command for a program like this


​# ../Src/configure FC=/export/apps/siesta/openmpi-1.8.8/bin/mpifort 
--with-blas=libopenblas.a --with-lapack=liblapack.a 
--with-scalapack=libscalapack.a

checking build system type... x86_64-unknown-linux-gnu
checking host system type... x86_64-unknown-linux-gnu
checking for Fortran compiler default output file name... a.out
checking whether the Fortran compiler works... configure: error: 
cannot run Fortran compiled programs.

If you meant to cross compile, use `--host'.
See `config.log' for more details.



The content of config.log is available at ​http://pastebin.com/LTxxRMwH

It seems that mpifort (the wrapper compiler) has different usage than 
previous mpif90


Any idea about that?


Regards,
Mahmood




___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users


___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
​>(i'd like to make sure you are not using IntelMPI libmpi.so.1 with Open
MPI libmpi_mpifh.so.2, that can happen if Intel MPI >appears first in your
LD_LIBRARY_PATH)

# echo $LD_LIBRARY_PATH
/opt/gridengine/lib/linux-x64:/opt/openmpi/lib
# ls /opt/openmpi/lib
libmpi.a libompitrace.a libotfaux.so.0.0.0
libvt-mpi.so.0.0.0
libmpi_cxx.a libompitrace.lalibotf.la
libvt-mpi-unify.a
libmpi_cxx.lalibompitrace.solibotf.so
libvt-mpi-unify.la
libmpi_cxx.solibompitrace.so.0  libotf.so.1
libvt-mpi-unify.so
libmpi_cxx.so.1  libompitrace.so.0.0.0  libotf.so.1.5.2
libvt-mpi-unify.so.0
libmpi_cxx.so.1.0.1  libopen-pal.a  libvt.a
libvt-mpi-unify.so.0.0.0
libmpi_f77.a libopen-pal.la libvt-hyb.a  libvt-mt.a
libmpi_f77.lalibopen-pal.so libvt-hyb.la libvt-mt.la
libmpi_f77.solibopen-pal.so.4   libvt-hyb.so libvt-mt.so
libmpi_f77.so.1  libopen-pal.so.4.0.0   libvt-hyb.so.0
libvt-mt.so.0
libmpi_f77.so.1.0.3  libopen-rte.a  libvt-hyb.so.0.0.0
libvt-mt.so.0.0.0
libmpi_f90.a libopen-rte.la libvt-java.la
libvt-pomp.a
libmpi_f90.lalibopen-rte.so libvt-java.so
libvt-pomp.la
libmpi_f90.solibopen-rte.so.4   libvt-java.so.0  libvt.so
libmpi_f90.so.1  libopen-rte.so.4.0.0   libvt-java.so.0.0.0  libvt.so.0
libmpi_f90.so.1.1.0  libotf.a   libvt.la
libvt.so.0.0.0
libmpi.lalibotfaux.alibvt-mpi.a  mpi.mod
libmpi.solibotfaux.la   libvt-mpi.la openmpi
libmpi.so.1  libotfaux.so   libvt-mpi.so pkgconfig
libmpi.so.1.0.3  libotfaux.so.0 libvt-mpi.so.0




It seems that there is another openmpi installation which has been
installed by previous admins.
Before removing /opt/openmpi, I would like to unset the LD_LIBRARY_PATH
first to see if it has any effect. Do you agree with that?

Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Gilles Gouaillardet 

That sounds good to me !

just to make it crystal clear ...

assuming you configure'd your Open MPI 1.8.8 with 
--enable-mpirun-prefix-by-default


(and if you did not, i do encourage you to do so), then all you need is 
to remove


/opt/openmpi/lib from your LD_LIBRARY_PATH

(e.g. you do *not* have to rm -rf /opt/openmpi)


Cheers,


Gilles


On 9/12/2016 4:30 PM, Mahmood Naderan wrote:
​>(i'd like to make sure you are not using IntelMPI libmpi.so.1 with 
Open MPI libmpi_mpifh.so.2, that can happen if Intel MPI >appears 
first in your LD_LIBRARY_PATH)


# echo $LD_LIBRARY_PATH
/opt/gridengine/lib/linux-x64:/opt/openmpi/lib
# ls /opt/openmpi/lib
libmpi.a libompitrace.a libotfaux.so.0.0.0   
libvt-mpi.so.0.0.0
libmpi_cxx.a libompitrace.la  libotf.la 
 libvt-mpi-unify.a
libmpi_cxx.la  libompitrace.solibotf.so 
libvt-mpi-unify.la 
libmpi_cxx.solibompitrace.so.0 libotf.so.1  
libvt-mpi-unify.so
libmpi_cxx.so.1  libompitrace.so.0.0.0 libotf.so.1.5.2  
libvt-mpi-unify.so.0
libmpi_cxx.so.1.0.1  libopen-pal.a libvt.a  
libvt-mpi-unify.so.0.0.0
libmpi_f77.a libopen-pal.la  
libvt-hyb.a  libvt-mt.a
libmpi_f77.la  libopen-pal.so libvt-hyb.la 
 libvt-mt.la 

libmpi_f77.solibopen-pal.so.4 libvt-hyb.so libvt-mt.so
libmpi_f77.so.1  libopen-pal.so.4.0.0 libvt-hyb.so.0   
libvt-mt.so.0

libmpi_f77.so.1.0.3  libopen-rte.a libvt-hyb.so.0.0.0   libvt-mt.so.0.0.0
libmpi_f90.a libopen-rte.la  libvt-java.la 
 libvt-pomp.a
libmpi_f90.la  libopen-rte.so 
libvt-java.so libvt-pomp.la 

libmpi_f90.solibopen-rte.so.4 libvt-java.so.0  libvt.so
libmpi_f90.so.1  libopen-rte.so.4.0.0 libvt-java.so.0.0.0  libvt.so.0
libmpi_f90.so.1.1.0  libotf.a libvt.la  libvt.so.0.0.0
libmpi.la  libotfaux.a
libvt-mpi.a  mpi.mod
libmpi.so libotfaux.la  libvt-mpi.la 
 openmpi

libmpi.so.1  libotfaux.so libvt-mpi.so pkgconfig
libmpi.so.1.0.3  libotfaux.so.0 libvt-mpi.so.0




It seems that there is another openmpi installation which has been 
installed by previous admins.
Before removing /opt/openmpi, I would like to unset the 
LD_LIBRARY_PATH first to see if it has any effect. Do you agree with that?


Regards,
Mahmood




___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users


___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
>​  --enable-mpirun-prefix-by-default​

What is that? Does that mean "configure 1.8.8 with the default one
installed on the system"? Then that is not good I think because


Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
>​  --enable-mpirun-prefix-by-default​

What is that? Does that mean "configure 1.8.8 with the default one
installed on the system"? Then that is not good I think because


# /opt/openmpi/bin/ompi_info
 Package: Open MPI root@centos-6-3.localdomain Distribution
Open MPI: 1.6.2




Regards,
Mahmood



On Mon, Sep 12, 2016 at 12:20 PM, Mahmood Naderan 
wrote:

> >​  --enable-mpirun-prefix-by-default​
>
> What is that? Does that mean "configure 1.8.8 with the default one
> installed on the system"? Then that is not good I think because
>
>
> Regards,
> Mahmood
>
>
>
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Gilles Gouaillardet 
Basically, it means libs with be linked with 
-Wl,-rpath,/export/apps/siesta/openmpi-1.8.8/lib


so if you run a.out with an empty $LD_LIBRARY_PATH, then it will look 
for the MPI libraries in

/export/apps/siesta/openmpi-1.8.8/lib


Cheers,


Gilles


On 9/12/2016 4:50 PM, Mahmood Naderan wrote:

>​ --enable-mpirun-prefix-by-default​

What is that? Does that mean "configure 1.8.8 with the default one 
installed on the system"? Then that is not good I think because



Regards,
Mahmood




___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users


___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Gilles Gouaillardet 

Mahmood,

I was suggesting you (re)configure (i assume you did it) the Open MPI 
1.8.8 installed in /export/apps/siesta/openmpi-1.8.8 with 
--enable-mpirun-prefix-by-default


Cheers,

Gilles

On 9/12/2016 4:51 PM, Mahmood Naderan wrote:

>​ --enable-mpirun-prefix-by-default​

What is that? Does that mean "configure 1.8.8 with the default one 
installed on the system"? Then that is not good I think because



# /opt/openmpi/bin/ompi_info
 Package: Open MPI root@centos-6-3.localdomain 
Distribution

Open MPI: 1.6.2




Regards,
Mahmood



On Mon, Sep 12, 2016 at 12:20 PM, Mahmood Naderan 
mailto:mahmood...@gmail.com>> wrote:


>​ --enable-mpirun-prefix-by-default​

What is that? Does that mean "configure 1.8.8 with the default one
installed on the system"? Then that is not good I think because


Regards,
Mahmood





___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users


___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
Is the following output OK?


...
Making install in util
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[3]: Nothing to be done for `install-exec-am'.
make[3]: Nothing to be done for `install-data-am'.
make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
make[3]: Nothing to be done for `install-exec-am'.
make[3]: Nothing to be done for `install-data-am'.
make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[1]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
make[2]: Nothing to be done for `install-exec-am'.
make[2]: Nothing to be done for `install-data-am'.
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
root@cluster:openmpi-1.8.8# ls bin/
mpic++ mpif90-vt orte-clean   otfcompress shmemrun
vtjava
mpicc  mpifort   ortedotfconfig   vtc++vtrun
mpiCC  mpifort-vtorte-infootfdecompress   vtcc
vtsetup
mpicc-vt   mpirunorte-ps  otfinfo vtCC
vtsetup.jar
mpiCC-vt   ompi-cleanorterun  otfmergevtcxx
vtunify
mpic++-vt  ompi_info orte-server  otfmerge-mpivtf77
vtunify-mpi
mpicxx ompi-ps   orte-top otfprintvtf90
vtwrapper
mpicxx-vt  ompi-server   oshccotfprofile  vtfilter
mpiexecompi-top  oshfort  otfprofile-mpi  vtfiltergen
mpif77 opal_wrapper  oshmem_info  otfshrink   vtfiltergen-mpi
mpif77-vt  opari oshrun   shmemcc vtfilter-mpi
mpif90 orteccotfaux   shmemfort   vtfort
root@cluster:openmpi-1.8.8# echo $LD_LIBRARY_PATH
/opt/gridengine/lib/linux-x64:/opt/openmpi/lib
root@cluster:openmpi-1.8.8# grep -r mpirun config.log
  $ ./configure --prefix=/export/apps/siesta/openmpi-1.8.8
--enable-mpirun-prefix-by-default
configure:66027: result:  '--prefix=/export/apps/siesta/openmpi-1.8.8'
'--enable-mpirun-prefix-by-default'
configure:97538: running /bin/sh './configure' --disable-dns --disable-http
--disable-rpc --disable-openssl --enable-thread-support --disable-evport
'--prefix=/export/apps/siesta/openmpi-1.8.8'
'--enable-mpirun-prefix-by-default' --cache-file=/dev/null --srcdir=.
--disable-option-checking
configure:290550: running /bin/sh './configure' --disable-option-checking
--with-openmpi-inside=1.7 '--prefix=/export/apps/siesta/openmpi-1.8.8'
'--enable-mpirun-prefix-by-default'
CPPFLAGS=-I/export/apps/siesta/openmpi-1.8.8/ompi/include
LDFLAGS=-L/export/apps/siesta/openmpi-1.8.8/ompi/.libs
--cache-file=/dev/null --srcdir=. --disable-option-checking
root@cluster:openmpi-1.8.8#






So I ran

# ./configure --prefix=/export/apps/siesta/openmpi-1.8.8
--enable-mpirun-prefix-by-default
# make
# make install

However, LD_LIBRARY_PATH still shows the previous install (/opt/openmpi)


Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Gilles Gouaillardet 

Mahmood,

you need to manually remove /opt/openmpi/lib from your LD_LIBRARY_PATH
(or have your sysadmin do it if this is somehow done automatically)

the point of configuring with --enable-mpirun-prefix-by-default is you 
do *not* need

to add /export/apps/siesta/openmpi-1.8.8/lib in your LD_LIBRARY_PATH

Cheers,

Gilles

On 9/12/2016 5:28 PM, Mahmood Naderan wrote:

Is the following output OK?


...
Making install in util
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[3]: Nothing to be done for `install-exec-am'.
make[3]: Nothing to be done for `install-data-am'.
make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
make[3]: Nothing to be done for `install-exec-am'.
make[3]: Nothing to be done for `install-data-am'.
make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
make[1]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
make[2]: Nothing to be done for `install-exec-am'.
make[2]: Nothing to be done for `install-data-am'.
make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
root@cluster:openmpi-1.8.8# ls bin/
mpic++ mpif90-vt orte-clean   otfcompress shmemrun vtjava
mpicc  mpifort   ortedotfconfig vtc++vtrun
mpiCC  mpifort-vtorte-infootfdecompress vtcc 
vtsetup

mpicc-vt   mpirunorte-ps  otfinfo vtCC vtsetup.jar
mpiCC-vt   ompi-cleanorterun  otfmerge vtcxxvtunify
mpic++-vt  ompi_info orte-server  otfmerge-mpi vtf77
vtunify-mpi

mpicxx ompi-ps   orte-top otfprint vtf90vtwrapper
mpicxx-vt  ompi-server   oshccotfprofile  vtfilter
mpiexecompi-top  oshfort  otfprofile-mpi vtfiltergen
mpif77 opal_wrapper  oshmem_info  otfshrink vtfiltergen-mpi
mpif77-vt  opari oshrun   shmemcc vtfilter-mpi
mpif90 orteccotfaux   shmemfort   vtfort
root@cluster:openmpi-1.8.8# echo $LD_LIBRARY_PATH
/opt/gridengine/lib/linux-x64:/opt/openmpi/lib
root@cluster:openmpi-1.8.8# grep -r mpirun config.log
  $ ./configure --prefix=/export/apps/siesta/openmpi-1.8.8 
--enable-mpirun-prefix-by-default
configure:66027: result: '--prefix=/export/apps/siesta/openmpi-1.8.8' 
'--enable-mpirun-prefix-by-default'
configure:97538: running /bin/sh './configure' --disable-dns 
--disable-http --disable-rpc --disable-openssl --enable-thread-support 
--disable-evport '--prefix=/export/apps/siesta/openmpi-1.8.8' 
'--enable-mpirun-prefix-by-default' --cache-file=/dev/null --srcdir=. 
--disable-option-checking
configure:290550: running /bin/sh './configure' 
--disable-option-checking --with-openmpi-inside=1.7 
'--prefix=/export/apps/siesta/openmpi-1.8.8' 
'--enable-mpirun-prefix-by-default' 
CPPFLAGS=-I/export/apps/siesta/openmpi-1.8.8/ompi/include 
LDFLAGS=-L/export/apps/siesta/openmpi-1.8.8/ompi/.libs 
--cache-file=/dev/null --srcdir=. --disable-option-checking

root@cluster:openmpi-1.8.8#






So I ran

# ./configure --prefix=/export/apps/siesta/openmpi-1.8.8 
--enable-mpirun-prefix-by-default

# make
# make install

However, LD_LIBRARY_PATH still shows the previous install (/opt/openmpi)


Regards,
Mahmood




___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users


___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
It seems that it is part of rocks-openmpi. I will find out how to remove it
and will come back.

Regards,
Mahmood



On Mon, Sep 12, 2016 at 1:06 PM, Gilles Gouaillardet 
wrote:

> Mahmood,
>
> you need to manually remove /opt/openmpi/lib from your LD_LIBRARY_PATH
> (or have your sysadmin do it if this is somehow done automatically)
>
> the point of configuring with --enable-mpirun-prefix-by-default is you do
> *not* need
> to add /export/apps/siesta/openmpi-1.8.8/lib in your LD_LIBRARY_PATH
>
> Cheers,
>
> Gilles
>
>
> On 9/12/2016 5:28 PM, Mahmood Naderan wrote:
>
> Is the following output OK?
>
>
> ...
> Making install in util
> make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
> make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test/util'
> make[3]: Nothing to be done for `install-exec-am'.
> make[3]: Nothing to be done for `install-data-am'.
> make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
> make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test/util'
> make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
> make[3]: Entering directory `/export/apps/siesta/openmpi-1.8.8/test'
> make[3]: Nothing to be done for `install-exec-am'.
> make[3]: Nothing to be done for `install-data-am'.
> make[3]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
> make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
> make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8/test'
> make[1]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
> make[2]: Entering directory `/export/apps/siesta/openmpi-1.8.8'
> make[2]: Nothing to be done for `install-exec-am'.
> make[2]: Nothing to be done for `install-data-am'.
> make[2]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
> make[1]: Leaving directory `/export/apps/siesta/openmpi-1.8.8'
> root@cluster:openmpi-1.8.8# ls bin/
> mpic++ mpif90-vt orte-clean   otfcompress shmemrun
> vtjava
> mpicc  mpifort   ortedotfconfig   vtc++
> vtrun
> mpiCC  mpifort-vtorte-infootfdecompress   vtcc
> vtsetup
> mpicc-vt   mpirunorte-ps  otfinfo vtCC
> vtsetup.jar
> mpiCC-vt   ompi-cleanorterun  otfmergevtcxx
> vtunify
> mpic++-vt  ompi_info orte-server  otfmerge-mpivtf77
> vtunify-mpi
> mpicxx ompi-ps   orte-top otfprintvtf90
> vtwrapper
> mpicxx-vt  ompi-server   oshccotfprofile  vtfilter
> mpiexecompi-top  oshfort  otfprofile-mpi  vtfiltergen
> mpif77 opal_wrapper  oshmem_info  otfshrink   vtfiltergen-mpi
> mpif77-vt  opari oshrun   shmemcc vtfilter-mpi
> mpif90 orteccotfaux   shmemfort   vtfort
> root@cluster:openmpi-1.8.8# echo $LD_LIBRARY_PATH
> /opt/gridengine/lib/linux-x64:/opt/openmpi/lib
> root@cluster:openmpi-1.8.8# grep -r mpirun config.log
>   $ ./configure --prefix=/export/apps/siesta/openmpi-1.8.8
> --enable-mpirun-prefix-by-default
> configure:66027: result:  '--prefix=/export/apps/siesta/openmpi-1.8.8'
> '--enable-mpirun-prefix-by-default'
> configure:97538: running /bin/sh './configure' --disable-dns
> --disable-http --disable-rpc --disable-openssl --enable-thread-support
> --disable-evport  '--prefix=/export/apps/siesta/openmpi-1.8.8'
> '--enable-mpirun-prefix-by-default' --cache-file=/dev/null --srcdir=.
> --disable-option-checking
> configure:290550: running /bin/sh './configure' --disable-option-checking
> --with-openmpi-inside=1.7 '--prefix=/export/apps/siesta/openmpi-1.8.8'
> '--enable-mpirun-prefix-by-default' CPPFLAGS=-I/export/apps/
> siesta/openmpi-1.8.8/ompi/include 
> LDFLAGS=-L/export/apps/siesta/openmpi-1.8.8/ompi/.libs
> --cache-file=/dev/null --srcdir=. --disable-option-checking
> root@cluster:openmpi-1.8.8#
>
>
>
>
>
>
> So I ran
>
> # ./configure --prefix=/export/apps/siesta/openmpi-1.8.8
> --enable-mpirun-prefix-by-default
> # make
> # make install
>
> However, LD_LIBRARY_PATH still shows the previous install (/opt/openmpi)
>
>
> Regards,
> Mahmood
>
>
>
>
> ___
> users mailing 
> listus...@lists.open-mpi.orghttps://rfd.newmexicoconsortium.org/mailman/listinfo/users
>
>
>
> ___
> users mailing list
> users@lists.open-mpi.org
> https://rfd.newmexicoconsortium.org/mailman/listinfo/users
>
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] Problem with specifying wrapper compiler mpifort

2016-09-12 Thread Mahmood Naderan 
OK. Running "module unload rocks-openmpi" and putting that in ~/.bashrc
will remove /opt/openmpi/lib from LD_LIBRARY_PATH.

Thanks Gilles for your help.

Regards,
Mahmood



On Mon, Sep 12, 2016 at 1:25 PM, Mahmood Naderan 
wrote:

> It seems that it is part of rocks-openmpi. I will find out how to remove
> it and will come back.
>
> Regards,
> Mahmood
>
>
>
> On Mon, Sep 12, 2016 at 1:06 PM, Gilles Gouaillardet 
> wrote:
>
>> Mahmood,
>>
>> you need to manually remove /opt/openmpi/lib from your LD_LIBRARY_PATH
>> (or have your sysadmin do it if this is somehow done automatically)
>>
>> the point of configuring with --enable-mpirun-prefix-by-default is you
>> do *not* need
>> to add /export/apps/siesta/openmpi-1.8.8/lib in your LD_LIBRARY_PATH
>>
>> Cheers,
>>
>> Gilles
>>
>>
>>
>
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

[OMPI users] MPI libraries

2016-09-12 Thread Mahmood Naderan 
Hi,
Trying to build a source code with newer versions of OpenMPI, I still have
some problems that weren't exist in previous versions.

In 1.6.5, I wrote something in a arch.make file which is used by Makefile

FC=/export/apps/siesta/openmpi-1.6.5/bin/mpif90
MPI_INTERFACE=libmpi_f90.a
MPI_INCLUDE=.

And then I had to copy that library to the local folder in order to drop
the full path.



However, with 1.8.8, it has been stated that mpifort (the wrapper) provides
all necssary libraries. So I now write

FC=/export/apps/siesta/openmpi-1.8.8/bin/mpifort
MPI_INTERFACE=
MPI_INCLUDE=.



However, the compilation of the program fails with

make[1]: Entering directory `/export/apps/siesta/siesta-4.0/spar/fdf'
In fdf, INCFLAGS is: -I/export/apps/siesta/siesta-4.0/Src/fdf  -I../
/export/apps/siesta/openmpi-1.8.8/bin/mpifort -c -g -Os
-I/export/apps/siesta/siesta-4.0/Src/fdf  -I../ -DMPI -DFC_HAVE_FLUSH
-DFC_HAVE_ABORT  /export/apps/siesta/siesta-4.0/Src/fdf/fdf.F90
/export/apps/siesta/siesta-4.0/Src/fdf/fdf.F90:498.20:

  use mpi_siesta
1
Fatal Error: Can't open module file 'mpi_siesta.mod' for reading at (1): No
such file or directory



It seems that it is trying to find an MPI library. Any idea about that?

Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] MPI libraries

2016-09-12 Thread Gilles Gouaillardet 
Mahmood,

mpi_siesta is a siesta library, not an Open MPI library.

fwiw, you might want to try again from scratch with
MPI_INTERFACE=libmpi_f90.a
DEFS_MPI=-DMPI
in your arch.make

i do not think libmpi_f90.a is related to an OpenMPI library.

if you need some more support, please refer to the siesta doc and/or ask on
a siesta mailing list


Cheers,

Gilles

On Monday, September 12, 2016, Mahmood Naderan  wrote:

> Hi,
> Trying to build a source code with newer versions of OpenMPI, I still have
> some problems that weren't exist in previous versions.
>
> In 1.6.5, I wrote something in a arch.make file which is used by Makefile
>
> FC=/export/apps/siesta/openmpi-1.6.5/bin/mpif90
> MPI_INTERFACE=libmpi_f90.a
> MPI_INCLUDE=.
>
> And then I had to copy that library to the local folder in order to drop
> the full path.
>
>
>
> However, with 1.8.8, it has been stated that mpifort (the wrapper)
> provides all necssary libraries. So I now write
>
> FC=/export/apps/siesta/openmpi-1.8.8/bin/mpifort
> MPI_INTERFACE=
> MPI_INCLUDE=.
>
>
>
> However, the compilation of the program fails with
>
> make[1]: Entering directory `/export/apps/siesta/siesta-4.0/spar/fdf'
> In fdf, INCFLAGS is: -I/export/apps/siesta/siesta-4.0/Src/fdf  -I../
> /export/apps/siesta/openmpi-1.8.8/bin/mpifort -c -g -Os
> -I/export/apps/siesta/siesta-4.0/Src/fdf  -I../ -DMPI -DFC_HAVE_FLUSH
> -DFC_HAVE_ABORT  /export/apps/siesta/siesta-4.0/Src/fdf/fdf.F90
> /export/apps/siesta/siesta-4.0/Src/fdf/fdf.F90:498.20:
>
>   use mpi_siesta
> 1
> Fatal Error: Can't open module file 'mpi_siesta.mod' for reading at (1):
> No such file or directory
>
>
>
> It seems that it is trying to find an MPI library. Any idea about that?
>
> Regards,
> Mahmood
>
>
>
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] MPI libraries

2016-09-12 Thread Mahmood Naderan 
>i do not think libmpi_f90.a is related to an OpenMPI library.


Thing is that, libmpi_f90.a is part of 1.6.5 and siesta use that. However,
1.8.8 has no such file. Instead it has some other names and you said before
that mpifort (the wrapper) will automatically use the necessary libraries.
Please see below:

# ls /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.*
/export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.a
/export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.la
/export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so
/export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so.1
/export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so.1.3.0


The Makefile of Siesta that use mpi interface is available at
http://pastebin.com/RQx3KpXp

Regards,
Mahmood
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] MPI libraries

2016-09-12 Thread Jeff Squyres (jsquyres) 
It might be easier to not list the MPI library that Open MPI is using -- we 
have changed the name of this library over time (as you have noticed).  The 
"mpifort" wrapper compiler will always pick up the right library name for you.


> On Sep 12, 2016, at 1:44 PM, Mahmood Naderan  wrote:
> 
> >i do not think libmpi_f90.a is related to an OpenMPI library.
> 
> 
> Thing is that, libmpi_f90.a is part of 1.6.5 and siesta use that. However, 
> 1.8.8 has no such file. Instead it has some other names and you said before 
> that mpifort (the wrapper) will automatically use the necessary libraries. 
> Please see below:
> 
> # ls /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.*
> /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.a
> /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.la
> /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so
> /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so.1
> /export/apps/computer/openmpi-1.6.5/lib/libmpi_f90.so.1.3.0
> 
> 
> The Makefile of Siesta that use mpi interface is available at 
> http://pastebin.com/RQx3KpXp
> 
> Regards,
> Mahmood
> 
> 
> ___
> users mailing list
> users@lists.open-mpi.org
> https://rfd.newmexicoconsortium.org/mailman/listinfo/users


-- 
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to: 
http://www.cisco.com/web/about/doing_business/legal/cri/

___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] MPI libraries

2016-09-12 Thread Dave Love 
Gilles Gouaillardet  writes:

> Mahmood,
>
> mpi_siesta is a siesta library, not an Open MPI library.
>
> fwiw, you might want to try again from scratch with
> MPI_INTERFACE=libmpi_f90.a
> DEFS_MPI=-DMPI
> in your arch.make
>
> i do not think libmpi_f90.a is related to an OpenMPI library.

libmpi_f90 is the Fortran 90 library in OMPI 1.6, but presumably you
want the shared, system version.

> if you need some more support, please refer to the siesta doc and/or ask on
> a siesta mailing list

I used the system MPI (which is OMPI 1.6 for historical reasons) and it
seems siesta 4.0 just built on RHEL6 with the rpm spec fragment below,
but I'm sure it would also work with 1.8.  (However, it needs cleaning
up significantly for the intended Fedora packaging.)

  %global _configure ../Src/configure
  cd Obj
  ../Src/obj_setup.sh
  %_openmpi_load
  %configure --enable-mpi
  make # not smp-safe

(%_openmpi_load just does "module load openmpi_x86_64" in this case.)
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users

Re: [OMPI users] MPI libraries

2016-09-12 Thread Mahmood Naderan 
OK. I will try that. Thanks for the suggestion.

Regards,
Mahmood



On Mon, Sep 12, 2016 at 11:35 PM, Dave Love  wrote:

> Gilles Gouaillardet  writes:
>
> > Mahmood,
> >
> > mpi_siesta is a siesta library, not an Open MPI library.
> >
> > fwiw, you might want to try again from scratch with
> > MPI_INTERFACE=libmpi_f90.a
> > DEFS_MPI=-DMPI
> > in your arch.make
> >
> > i do not think libmpi_f90.a is related to an OpenMPI library.
>
> libmpi_f90 is the Fortran 90 library in OMPI 1.6, but presumably you
> want the shared, system version.
>
> > if you need some more support, please refer to the siesta doc and/or ask
> on
> > a siesta mailing list
>
> I used the system MPI (which is OMPI 1.6 for historical reasons) and it
> seems siesta 4.0 just built on RHEL6 with the rpm spec fragment below,
> but I'm sure it would also work with 1.8.  (However, it needs cleaning
> up significantly for the intended Fedora packaging.)
>
>   %global _configure ../Src/configure
>   cd Obj
>   ../Src/obj_setup.sh
>   %_openmpi_load
>   %configure --enable-mpi
>   make # not smp-safe
>
> (%_openmpi_load just does "module load openmpi_x86_64" in this case.)
> ___
> users mailing list
> users@lists.open-mpi.org
> https://rfd.newmexicoconsortium.org/mailman/listinfo/users
>
___
users mailing list
users@lists.open-mpi.org
https://rfd.newmexicoconsortium.org/mailman/listinfo/users