Skip to main content

MPI for Python

Project description

This package provides Python bindings for the Message Passing Interface (MPI) standard. It is implemented on top of the MPI-1/2/3 specification and exposes an API which grounds on the standard MPI-2 C++ bindings.

Features

This package supports:

  • Convenient communication of any picklable Python object
    • point-to-point (send & receive)
    • collective (broadcast, scatter & gather, reductions)
  • Fast communication of Python object exposing the Python buffer interface (NumPy arrays, builtin bytes/string/array objects)
    • point-to-point (blocking/nonbloking/persistent send & receive)
    • collective (broadcast, block/vector scatter & gather, reductions)
  • Process groups and communication domains
    • Creation of new intra/inter communicators
    • Cartesian & graph topologies
  • Parallel input/output:
    • read & write
    • blocking/nonbloking & collective/noncollective
    • individual/shared file pointers & explicit offset
  • Dynamic process management
    • spawn & spawn multiple
    • accept/connect
    • name publishing & lookup
  • One-sided operations
    • remote memory access (put, get, accumulate)
    • passive target syncronization (start/complete & post/wait)
    • active target syncronization (lock & unlock)

Install

Once you have a working MPI implementation and the mpicc compiler wrapper is on your search path, you can install this package

  • using pip:

    $ pip install mpi4py
    
  • using easy_install (deprecated):

    $ easy_install mpi4py
    

You can also install the in-development version of mpi4py

  • using pip:

    $ pip install git+https://bitbucket.org/mpi4py/mpi4py
    

    or:

    $ pip install https://bitbucket.org/mpi4py/mpi4py/get/master.tar.gz
    
  • using easy_install (deprecated):

    $ easy_install git+https://bitbucket.org/mpi4py/mpi4py
    

    or:

    $ easy_install https://bitbucket.org/mpi4py/mpi4py/get/master.tar.gz
    

You can also install it directly on Fedora and RHEL (and their derivatives) using the EPEL software repository

  • using yum and the openmpi package on x86_64:

    # yum install mpi4py-openmpi
    
  • using yum and the mpich package on x86_64:

    # yum install mpi4py-mpich
    

Please remember to load the correct module for your choosen MPI environment

  • for openmpi package on x86_64 do:

    $ module load mpi/openmpi-x86_64
    $ python -c "import mpi4py"
    
  • for mpich package on x86_64 do:

    $ module load mpi/mpich-x86_64
    $ python -c "import mpi4py"
    

    Note however, that the later doesn’t work on RHEL (and their derivatives) because of this bug and you need to manually adjust your PYTHONPATH accordingly.

Citations

If MPI for Python been significant to a project that leads to an academic publication, please acknowledge that fact by citing the project.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
mpi4py-2.0.0-cp26-none-win32.whl (319.0 kB) Copy SHA256 hash SHA256 Wheel cp26 Oct 18, 2015
mpi4py-2.0.0-cp26-none-win_amd64.whl (387.1 kB) Copy SHA256 hash SHA256 Wheel cp26 Oct 18, 2015
mpi4py-2.0.0-cp27-none-win32.whl (318.3 kB) Copy SHA256 hash SHA256 Wheel cp27 Oct 18, 2015
mpi4py-2.0.0-cp27-none-win_amd64.whl (385.3 kB) Copy SHA256 hash SHA256 Wheel cp27 Oct 18, 2015
mpi4py-2.0.0-cp33-none-win32.whl (320.5 kB) Copy SHA256 hash SHA256 Wheel cp33 Oct 18, 2015
mpi4py-2.0.0-cp33-none-win_amd64.whl (378.2 kB) Copy SHA256 hash SHA256 Wheel cp33 Oct 18, 2015
mpi4py-2.0.0-cp34-none-win32.whl (320.3 kB) Copy SHA256 hash SHA256 Wheel cp34 Oct 18, 2015
mpi4py-2.0.0-cp34-none-win_amd64.whl (378.3 kB) Copy SHA256 hash SHA256 Wheel cp34 Oct 18, 2015
mpi4py-2.0.0-cp35-none-win32.whl (305.3 kB) Copy SHA256 hash SHA256 Wheel cp35 Oct 18, 2015
mpi4py-2.0.0-cp35-none-win_amd64.whl (375.5 kB) Copy SHA256 hash SHA256 Wheel cp35 Oct 18, 2015
mpi4py-2.0.0.tar.gz (1.3 MB) Copy SHA256 hash SHA256 Source None Oct 18, 2015

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page