[mvapich-discuss] PGI -pthread switch

[Jonathan Perkins]

Can you post your config.log?  I think there is a linking issue that is
preventing the configure tests from being able to run and determine the
size of the integers.

On Mon, Mar 16, 2015 at 9:51 PM Matthew Russell <matthew.g.russell at gmail.com>
wrote:

> Ooh.. I thought the -pthread would have been contained within the mvapich2
> build files.  I actually got around this problem after a few hours by
> simply wrapping my PGI compilers with a script that filtered out the flag.
>
> That said, afterwards I attempted to build the same version but with
> pgi2013, and ran into a host of different problems, namely:
> ...
> checking for double _Complex... yes
> checking for long double _Complex... yes
> checking for size of Fortran type integer... configure: WARNING: Unable to
> compile the C routine for finding the size of a integer
>
> checking for size of Fortran type real... configure: WARNING: Unable to
> compile the C routine for finding the size of a real
>
> checking for size of Fortran type double precision... configure: WARNING:
> Unable to compile the C routine for finding the size of a double precision
>
> checking whether integer*1 is supported... yes
> checking whether integer*2 is supported... yes
> checking whether integer*4 is supported... yes
> checking whether integer*8 is supported... yes
> checking whether integer*16 is supported... yes
> checking whether real*4 is supported... yes
> checking whether real*8 is supported... yes
> checking whether real*16 is supported... yes
> *configure: error: Unable to configure with Fortran support because
> configure could not determine the size of a Fortran INTEGER.  Consider
> setting CROSS_F77_SIZEOF_INTEGER to the length in bytes of a Fortran
> INTEGER*
>
>
>  I tried some tricks on the PGI forum to no avail.  Is there any way to
> get past this?
>
> Thanks!
>
>
> On 16 March 2015 at 21:23, Jonathan Perkins <perkinjo at cse.ohio-state.edu>
> wrote:
>
>> Hello Matthew.   I think this -pthread flag might be being added from a
>> libtool file installed into your system.  When executing your make command
>> can you add V=1 to make it verbose.
>>
>> Something like:
>> make V=1
>>
>> One of the libraries being linked in when building libmpi should be
>> responsible.  Maybe one of the infiniband libraries or libcr if blcr is
>> installed on your system.
>>
>> One other thing you can do to check is to do something like:
>> find /usr/lib64 -name '*.la' | xargs grep -l pthread
>>
>> The above command should give you a potential list of offenders.  Please
>> let us know what you find.
>>
>> On Mon, Mar 16, 2015 at 9:17 PM Matthew Russell <
>> matthew.g.russell at gmail.com> wrote:
>>
>>> Hi,
>>>
>>> I can't seem to build mvpich2 v2.1rc2 (or rc1) due to:
>>>
>>> make[2]: Entering directory
>>> `/cm/shared/apps/mvapich2/pgi/64/2015/2.1rc2/mvapich2-2.1rc2'
>>>   GEN      lib/libmpi.la
>>> pgf77-Error-Unknown switch: -pthread
>>> make[2]: *** [lib/libmpi.la] Error 1
>>>
>>> I tried following advice in the list such as:
>>>
>>> http://mailman.cse.ohio-state.edu/pipermail/mvapich-discuss/2014-January/004779.html
>>>
>>> I removed every instance of -pthread I could find, even wrote a script
>>> to remove everything.  Specifically in,
>>>
>>> confdb/ltmain.sh contrib/hwloc/src/libhwloc_embedded.la
>>> contrib/hwloc/config/ltmain.sh contrib/hwloc/libtool limic2-0.5.6/ltmain.sh
>>> src/pm/hydra/mpl/confdb/ltmain.sh
>>> src/pm/hydra/tools/topo/hwloc/hwloc/config/ltmain.sh
>>> src/pm/hydra/confdb/ltmain.sh src/mpl/confdb/ltmain.sh src/mpl/libtool
>>> src/openpa/src/opa_primitives.h src/openpa/confdb/ltmain.sh
>>> src/openpa/libtool src/mpi/romio/confdb/ltmain.sh src/mpi/romio/libtool
>>> src/mpi/romio/libromio.la libch3affinity.la
>>>
>>> In my source directory I have:
>>> [matt at dena mvapich2-2.1rc2]$ grep -rnis -- -pthread *
>>> [matt at dena mvapich2-2.1rc2]$
>>>
>>>
>>> I also added -noswitcherror to FCFLAGS and FFLAGS
>>>
>>> But no matter what, I still get this error.
>>>
>>> I have no idea where it's getting this flag.
>>> _______________________________________________
>>> mvapich-discuss mailing list
>>> mvapich-discuss at cse.ohio-state.edu
>>> http://mailman.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20150317/ed6a1d2c/attachment-0004.html>