I have downloaded the nightly snapshot tarball of october 10th 2018 for
the 3.1 version and it solves the memory problem.
I ran my test case on 1, 2, 4, 10, 16, 20, 32, 40, and 64 cores
successfully.
This version also allows to compile my prerequisites libraries, so we
can use it out of the box to stay in production.
This allow me time to update hdf5, but also petsc/slepc libs, to works
with more recent MPI standard and moving to OpenMPI4.x versions.

Thanks for all your precious advices.

Patrick

Le 11/10/2018 à 17:19, Jeff Squyres (jsquyres) a écrit :
> Patrick --
>
> You might want to update your HDF code to not use MPI_LB and MPI_UB -- these 
> constants were deprecated in MPI-2.1 in 2009 (an equivalent function, 
> MPI_TYPE_CREATE_RESIZED was added in MPI-2.0 in 1997), and were removed from 
> the MPI-3.0 standard in 2012.
>
> Meaning: the death of these constants has been written on the wall since 2009.
>
> That being said, Open MPI v4.0 did not remove these constants -- we just 
> *disabled them by default*, specifically for cases like this.  I.e., we want 
> to make the greater MPI community aware that:
>
> 1) there are MPI-1 constructs that were initially deprecated and finally 
> removed from the standard (this happened years ago)
> 2) MPI applications should start moving away from these removed MPI-1 
> constructs
> 3) Open MPI is disabling these removed MPI-1 constructs by default in Open 
> MPI v4.0.  The current plan is to actually fully remove these MPI-1 
> constructs in Open MPI v5.0 (perhaps in 2019?).
>
> For the v4.0.x series, you can configure/build Open MPI with 
> --enable-mpi1-compatibility to re-activate MPI_LB and MPI_UB.
>
>
>
>> On Oct 11, 2018, at 10:58 AM, Patrick Begou 
>> <patrick.be...@legi.grenoble-inp.fr> wrote:
>>
>> Hi Jeff and George
>>
>> thanks for your answer. I find some time to work again on this problem dans 
>> I have downloaded OpenMPI 4.0.0rc4. It compiles without any problem but 
>> building the first dependance of my code (hdf5 1.8.12) with this version 4 
>> fails:
>>
>> ../../src/H5Smpio.c:355:28: error: 'MPI_LB' undeclared (first use in this 
>> function); did you mean 'MPI_IO'?
>>              old_types[0] = MPI_LB;
>>                             ^~~~~~
>>                             MPI_IO
>> ../../src/H5Smpio.c:355:28: note: each undeclared identifier is reported 
>> only once for each function it appears in
>> ../../src/H5Smpio.c:357:28: error: 'MPI_UB' undeclared (first use in this 
>> function); did you mean 'MPI_LB'?
>>              old_types[2] = MPI_UB;
>>                             ^~~~~~
>>                             MPI_LB
>> ../../src/H5Smpio.c:365:24: warning: implicit declaration of function 
>> 'MPI_Type_struct'; did you mean 'MPI_Type_size_x'? 
>> [-Wimplicit-function-declaration]
>>              mpi_code = MPI_Type_struct(3,               /* count */
>>                         ^~~~~~~~~~~~~~~
>>                         MPI_Type_size_x
>>
>> It is not possible for me to use a more recent hdf5 version as the API as 
>> changed and will not work with the code, even in compatible mode.
>>
>> At this time, I'll try version 3 from the git repo if I have the required 
>> tools available on my server. All prerequisites compile successfully with 
>> 3.1.2.
>>
>> Patrick
>>
>> -- 
>> ===================================================================
>> |  Equipe M.O.S.T.         |                                      |
>> |  Patrick BEGOU           | mailto:patrick.be...@grenoble-inp.fr |
>> |  LEGI                    |                                      |
>> |  BP 53 X                 | Tel 04 76 82 51 35                   |
>> |  38041 GRENOBLE CEDEX    | Fax 04 76 82 52 71                   |
>> ===================================================================
>>
>

_______________________________________________
users mailing list
users@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/users

Reply via email to