Hi Toby, can you try with a fully distributed vector (without ghost values) instead? Does that work?
On Wed, Jul 25, 2012 at 9:45 AM, Toby D. Young <[email protected]> wrote: > > > Greetings, > > I am running an application based on the step-40 distributed model. > I would like to perform the operation <v,Au> (vector-matrix-vector > multiplication). At the end of solve () function I have added: > const double > norm=system_matrix.matrix_scalar_product(locally_relevant_solution,locally_relevant_solution); > which works fine if (n_mpi_processes==1). > > How can this be done with n_mpi_processes>1? > > The (truncated) error message I get is: > > [1]PETSC ERROR: --------------------- Error Message > ------------------------------------ [0]PETSC ERROR: [1]PETSC ERROR: > Nonconforming object sizes! [1]PETSC ERROR: Mat mat,Vec y: local dim > 4160 8450! [1]PETSC ERROR: > ------------------------------------------------------------------------ > [1]PETSC ERROR: MatMult() line 2083 > in /home/tyoung/research.dev/petsc-dev/src/mat/interface/matrix.c > ---------------------------------------------------- Exception on > processing: -------------------------------------------------------- > An error occurred in line <512> of file > </home/tyoung/research.dev/deal.II/source/lac/petsc_matrix_base.cc> in > function void > dealii::PETScWrappers::MatrixBase::vmult(dealii::PETScWrappers::VectorBase&, > const dealii::PETScWrappers::VectorBase&) const The violated condition > was: ierr == 0 The name and call sequence of the exception was: > ExcPETScError(ierr) Additional Information: > An error with error number 60 occurred while calling a PETSc function > -------------------------------------------------------- > > Confused. I am not sure how to deal with this. > > Why is the locally_relevant_solution.size () and > ()completely_distributed_solution.size () reported to be twice the size > of the distributed matrix? Are the vectors not distributed? > > viz. PETSC ERROR: Mat mat,Vec y: local dim 4160 8450 (on two processes). > > Any ideas please? > > Best, > Toby > > > > > -- > Toby D. Young > > Assistant Professor Philosophy & Physics > Polish Academy of Sciences > www: http://www.ippt.gov.pl/~tyoung > skype: stenografia > > _______________________________________________ > dealii mailing list http://poisson.dealii.org/mailman/listinfo/dealii -- Timo Heister http://www.math.tamu.edu/~heister/ _______________________________________________ dealii mailing list http://poisson.dealii.org/mailman/listinfo/dealii
