Hy, If, by any bad luck, you use any of the following FORTRAN function
MPI_FILE_GET_POSITION MPI_FILE_GET_SIZE MPI_FILE_GET_VIEW MPI_TYPE_EXTENT they all are stiil overflowing (http://www.open-mpi.org/community/lists/devel/2010/12/8797.php) because they cast the correct result to MPI_Fint which default size if 32 bits. Yves Secretan yves.secre...@ete.inrs.ca Avant d'imprimer, pensez à l'environnement -----Message d'origine----- De : users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] De la part de Ricardo Reis Envoyé : 15 mai 2012 04:29 À : Open MPI Users Objet : Re: [OMPI users] MPI-IO puzzlement Hi all The problem has been found. I'm trying to use MPI-IO to write the file with all processes taking part in the calculation writing their bit. Here lies the rub. Each process has to write a piece of DIM = 35709696 elements. Using 64 processes the ofsett is my_rank * dim and so... the ofset size, for last processes becomes. DBG: 60 will WriteMPI_IO. dim 35709696 offset 2142581760 DBG: 61 will WriteMPI_IO. dim 35709696 offset -2116675840 DBG: 62 will WriteMPI_IO. dim 35709696 offset -2080966144 DBG: 63 will WriteMPI_IO. dim 35709696 offset -2045256448 offset is of the type MPI_OFFSET_KIND which seems insuficient to hold the correct size for the offset. So... am I condemned to write my own MPI data type so I can write the files? ideas... ? best regards, Ricardo Reis 'Non Serviam' PhD/MSc Mechanical Engineering | Lic. Aerospace Engineering Computational Fluid Dynamics, High Performance Computing, Turbulence http://www.lasef.ist.utl.pt Cultural Instigator @ Rádio Zero http://www.radiozero.pt http://www.flickr.com/photos/rreis/ contacts: gtalk: kyriu...@gmail.com skype: kyriusan Institutional Address: Ricardo J.N. dos Reis IDMEC, Instituto Superior Técnico, Technical University of Lisbon Av. Rovisco Pais 1049-001 Lisboa Portugal - email sent with alpine 2.00 -
