Skip to content

An easy-to-implement python library plugin for mpi4py along with worked examples designed to streamline domain decomposition and add a simplifying layer to noncontiguous MPI parallelization of multidimensional datasets.

License

Notifications You must be signed in to change notification settings

raboonik/AutoParallelizePy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AutoParallelizePy

An easy-to-implement python library plugin for mpi4py along with worked examples designed to streamline domain decomposition and add a simplifying layer to noncontiguous MPI parallelization of multidimensional datasets.

Author information

Abbas Raboonik

Email: [email protected]

Git: https://github.com/raboonik

Installation

Step 0

Make sure the following python3 packages are installed

     Numpy

     mpi4py

Step 1

  1. Make the installation script (install.sh) executable by running

    chmod +x install.sh

  1. To install under a specific directory run (do not run as root)

    ./install.sh path/to/directory

    or to install under the default directory simply execute

    ./install.sh

Step 2

Run "add2path.sh" to automatically update the python enviornment by executing

    . ./add2path.sh

Uninstallation

To uninstall and update the python environment simply run

    . ./uninstall.sh

Worked examples

After installation, to run the worked examples

     cd examples

     mpirun -n [number of cores] python3 [exampleName].py

About

An easy-to-implement python library plugin for mpi4py along with worked examples designed to streamline domain decomposition and add a simplifying layer to noncontiguous MPI parallelization of multidimensional datasets.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published