You need to have the following software properly installed to develop MPI for Python:

  • Python 3.6 or above.

  • The Cython compiler.

  • A working MPI implementation like MPICH or Open MPI, preferably supporting MPI-4 and built with shared/dynamic libraries.

Optionally, consider installing the following packages:

  • NumPy for enabling comprehensive testing of MPI communication.

  • CuPy for enabling comprehensive testing with a GPU-aware MPI.

  • Sphinx to build the documentation.


Most routine development tasks like building, installing in editable mode, testing, and generating documentation can be performed with the spin developer tool. Run spin at the top level source directory for a list of available subcommands.


MPI for Python uses setuptools-based build system that relies on the file. Some setuptools commands (e.g., build) accept additional options:


Lets you pass a section with MPI configuration within a special configuration file. Alternatively, you can use the MPICFG environment variable.


Specify the path or name of the mpicc C compiler wrapper. Alternatively, use the MPICC environment variable.


Specify the full path or name for the MPI-aware C linker. Alternatively, use the MPILD environment variable. If not set, the mpicc C compiler wrapper is used for linking.


Runs exhaustive tests for checking about missing MPI types, constants, and functions. This option should be passed in order to build MPI for Python against old MPI-1, MPI-2, or MPI-3 implementations, possibly providing a subset of MPI-4.

If you use a MPI implementation providing a mpicc C compiler wrapper (e.g., MPICH or Open MPI), it will be used for compilation and linking. This is the preferred and easiest way to build MPI for Python.

If mpicc is found in the executable search path (PATH environment variable), simply run the build command:

$ python build

If mpicc is not in your search path or the compiler wrapper has a different name, you can run the build command specifying its location, either via the --mpicc command option or using the MPICC environment variable:

$ python build --mpicc=/path/to/mpicc
$ env MPICC=/path/to/mpicc python build

Alternatively, you can provide all the relevant information about your MPI implementation by editing the mpi.cfg file located in the top level source directory. You can use the default section [mpi] or add a new custom section, for example [vendor_mpi] (see the examples provided in the mpi.cfg file as a starting point to write your own section):

include_dirs         = /usr/local/mpi/include
libraries            = mpi
library_dirs         = /usr/local/mpi/lib
runtime_library_dirs = /usr/local/mpi/lib

include_dirs         = /opt/mpi/include ...
libraries            = mpi ...
library_dirs         = /opt/mpi/lib ...
runtime_library_dirs = /opt/mpi/lib ...


and then run the build command specifying you custom configuration section:

$ python build --mpi=vendor_mpi
$ env MPICFG=vendor_mpi python build


MPI for Python can be installed in editable mode:

$ python -m pip install --editable .

After modifying Cython sources, an in-place rebuild is needed:

$ python build --inplace


To quickly test the installation:

$ mpiexec -n 5 python -m mpi4py.bench helloworld
Hello, World! I am process 0 of 5 on localhost.
Hello, World! I am process 1 of 5 on localhost.
Hello, World! I am process 2 of 5 on localhost.
Hello, World! I am process 3 of 5 on localhost.
Hello, World! I am process 4 of 5 on localhost.

$ mpiexec -n 5 python -m mpi4py.bench ringtest -l 10 -n 1048576
time for 10 loops = 0.00361614 seconds (5 processes, 1048576 bytes)

If you installed from a git clone or the source distribution, issuing at the command line:

$ mpiexec -n 5 python demo/

will launch a five-process run of the Python interpreter and run the demo script demo/ from the source distribution.

You can also run all the unittest scripts:

$ mpiexec -n 5 python test/

or, if you have the pytest unit testing framework installed:

$ mpiexec -n 5 pytest