Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2005-11-22 11:58:23


Yes. I actually announced last night on the devel list that 1.0.1 will
be forthcoming shortly. During the release process, I goofed and
accidentally left out a shared memory bug fix (it's on the trunk; it
didn't make it to the v1.0 branch before release). The bug only shows
up on specific platforms -- basically, if you can successfully complete
MPI_INIT, everything is fine (i.e., the bug fix is not critical for
you). But if you seg fault in the shared memory setup during MPI_INIT,
your platform needs the bug fix that is coming in 1.0.1.

Here's what we have in the NEWS file for 1.0.1:

- Fix missing MPI_F_STATUS_IGNORE and MPI_F_STATUSES_IGNORE
   instanatiations. Thanks to Anthony Chan for pointing this out.
- Add a missing value for MPI_WIN_NULL in mpif.h.
- Bring over some fixes for the sm btl that somehow didn't make it
   over from the trunk before v1.0. Thanks to Beth Tibbitts and Bill
   Chung for helping identify this issue.
- Bring over some fixes for the iof that somehow didn't make it over
   from the trunk before v1.0.
- Fix for --with-wrapper-ldflags handling. Thanks to Dries Kimpe for
   pointing this out to us.

On Nov 22, 2005, at 11:42 AM, Anthony Chan wrote:

>
> Thanks for fixing this. Will there be a patched release of openmpi
> that will contain this fix anytime soon ? (In the meantime, I could
> do a
> anonymous read on the svn repository.)
>
> A.Chan
>
> On Tue, 22 Nov 2005, Jeff Squyres wrote:
>
>> Whoops! We forgot to instantiate these -- thanks for catching that.
>>
>> I have just committed fixes to both the trunk and the v1.0 branch.
>> This also prompted the addition of the following text in the README
>> file:
>>
>> -----
>> - Open MPI will build bindings suitable for all common forms of
>> Fortran 77 compiler symbol mangling on platforms that support it
>> (e.g., Linux). On platforms that do not support weak symbols
>> (e.g.,
>> OS X), Open MPI will build Fortran 77 bindings just for the
>> compiler
>> that Open MPI was configured with.
>>
>> Hence, on platforms that support it, if you configure Open MPI with
>> a Fortran 77 compiler that uses one symbol mangling scheme, you can
>> successfully compile and link MPI Fortran 77 applications with a
>> Fortran 77 compiler that uses a different symbol mangling scheme.
>>
>> NOTE: For platforms that support the multi-Fortran-compiler
>> bindings
>> (i.e., weak symbols are supported), due to limitations in the MPI
>> standard and in Fortran compilers, it is not possible to hide these
>> differences in all cases. Specifically, the following two cases
>> may
>> not be portable between different Fortran compilers:
>>
>> 1. The C constants MPI_F_STATUS_IGNORE and MPI_F_STATUSES_IGNORE
>> will only compare properly to Fortran applications that were
>> created with Fortran compilers that that use the same
>> name-mangling scheme as the Fortran compiler that Open MPI was
>> configured with.
>>
>> 2. Fortran compilers may have different values for the logical
>> .TRUE. constant. As such, any MPI function that uses the
>> fortran
>> LOGICAL type may only get .TRUE. values back that correspond to
>> the the .TRUE. value of the Fortran compiler that Open MPI was
>> configured with.
>>
>> You can use the ompi_info command to see the Fortran compiler that
>> Open MPI was configured with.
>> -----
>>
>>
>> On Nov 22, 2005, at 12:49 AM, Anthony Chan wrote:
>>
>>>
>>> Hi
>>>
>>> Linking the following program with mpicc from openmpi-1.0 compiled
>>> with gcc-4.0 on a IA32 linux box
>>>
>>> *************************
>>> #include <stdio.h>
>>> #include "mpi.h"
>>>
>>> int main() {
>>>
>>> int argc; char **argv;
>>>
>>> MPI_Fint *f_status;
>>> ;
>>> MPI_Init(&argc, &argv);
>>>
>>> f_status = MPI_F_STATUS_IGNORE;
>>> f_status = MPI_F_STATUSES_IGNORE;
>>>
>>> MPI_Finalize();
>>>
>>> ; return 0; }
>>> **************************
>>>
>>> with command "<openmpi-1.0>/bin/mpicc ts_MPI_F_STATUS_IGNORE.c"
>>> produces
>>> unresolved references of MPI_F_STATUS(ES)_IGNORE (which are both
>>> defined
>>> in mpi.h).
>>>
>>> Here is ompi_info:
>>>
>>> Open MPI: 1.0r8189 Open MPI SVN revision: r8189
>>> Open RTE: 1.0r8189
>>> Open RTE SVN revision: r8189
>>> OPAL: 1.0r8189
>>> OPAL SVN revision: r8189
>>> ...
>>> Configured architecture: i686-pc-linux-gnu
>>> C bindings: yes
>>> C++ bindings: yes
>>> Fortran77 bindings: yes (all)
>>> Fortran90 bindings: yes
>>> C compiler: /soft/apps/packages/gcc-4.0.0/bin/gcc-4.0
>>> C compiler absolute: /soft/apps/packages/gcc-4.0.0/bin/gcc-4.0
>>> C++ compiler: /soft/apps/packages/gcc-4.0.0/bin/g++-4.0
>>> C++ compiler absolute: /soft/apps/packages/gcc-4.0.0/bin/g++-4.0
>>> Fortran77 compiler:
>>> /soft/apps/packages/gcc-4.0.0/bin/gfortran-4.0
>>> Fortran77 compiler abs:
>>> /soft/apps/packages/gcc-4.0.0/bin/gfortran-4.0
>>> Fortran90 compiler:
>>> /soft/apps/packages/gcc-4.0.0/bin/gfortran-4.0
>>> Fortran90 compiler abs:
>>> /soft/apps/packages/gcc-4.0.0/bin/gfortran-4.0
>>> C profiling: yes
>>> C++ profiling: yes
>>> Fortran77 profiling: yes
>>> Fortran90 profiling: yes
>>> C++ exceptions: no
>>> Thread support: posix (mpi: no, progress: no)
>>> Internal debug support: no
>>> MPI parameter check: runtime
>>> Memory profiling support: no
>>> Memory debugging support: no
>>> libltdl support: 1
>>> ...
>>>
>>>
>>> A.Chan
>>> _______________________________________________
>>> users mailing list
>>> users_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>>
>>
>> --
>> {+} Jeff Squyres
>> {+} The Open MPI Project
>> {+} http://www.open-mpi.org/
>>
>> _______________________________________________
>> users mailing list
>> users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users
>

-- 
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/