Skip to content
Snippets Groups Projects
Select Git revision
  • ed87b407a05e2427c1979c517b36da4fec56a5dd
  • master default protected
  • releases/2.8
  • feature/autodiff
  • feature/hyperdual-vector-mode
  • finite-strain-plasticity
  • patrizio-convexity-test
  • releases/2.6-1
  • releases/2.5-1
  • releases/2.4-1
  • releases/2.3-1
  • releases/2.2-1
  • releases/2.1-1
  • releases/2.0-1
  • subversion->git
15 results

elasticity

  • Clone with SSH
  • Clone with HTTPS
    • Forked from agnumpde / dune-elasticity
    Source project has a limited visibility.
    user avatar
    MPI_Sendrecv_replace: correctly handle large data
    Gilles Gouaillardet authored 
    Because MPI_Sendrecv_replace() uses PMPI_Sendrecv() with MPI_PACKED
under the hood, the data to be exchanged size = MPI_Type_size(datatype) * count
must fit in a signed integer.
Otherwise, PMPI_Sendrecv()
 - fails with an error message if (int)size < 0
 - silently truncate the data if (int)size >= 0

Refs. open-mpi/ompi#8862

Thanks Jakub Benda for reporting this issue and suggesting a fix.

Signed-off-by: default avatarGilles Gouaillardet <gilles@rist.or.jp>
    6a11873e
    History
    user avatar 6a11873e
    History
    Code owners
    Assign users and groups as approvers for specific file changes. Learn more.
    Name Last commit Last update
    ..