This exercise is similar to exercise J1D-PtP-Blocking and basic descriptions are not reiterated. The goal is to use nonblocking point-to-point communications for the halo exchange so that neither deadlock nor serialization can be an issue. Furthermore, this exercise shows how can one overlap computation and communication using nonblocking calls.

  • In the directory J1D-PtP-Nonblocking, there are f and c subdirectories for Fortran and C, respectively. If you have loaded the modules as described in exercise Hello, compilers and MPI wrappers are ready for use. The compilation process is facilitated using a Makefile.
  • There are 9 FIXME markers most of which are related to the MPI nonblocking procedure calls.
  • You can use the same reference domain file from exercise J1D-PtP-Blocking to validate your solution of the exercise.

Last modified: Sunday, 31 March 2024, 9:30 PM