mpi4py-fft
----------
.. image:: https://dev.azure.com/mpi4py/mpi4py-fft/_apis/build/status/mpi4py.mpi4py-fft?branchName=master
:target: https://dev.azure.com/mpi4py/mpi4py-fft
.. image:: https://codecov.io/bb/mpi4py/mpi4py-fft/branch/master/graph/badge.svg
:target: https://codecov.io/bb/mpi4py/mpi4py-fft
.. image:: https://readthedocs.org/projects/mpi4py-fft/badge/?version=latest
:target: https://mpi4py-fft.readthedocs.io/en/latest/?badge=latest
:alt: Documentation Status
.. image:: https://anaconda.org/conda-forge/mpi4py-fft/badges/downloads.svg
:target: https://anaconda.org/conda-forge/mpi4py-fft
:alt: Total downloads from conda-forge
mpi4py-fft is a Python package for computing Fast Fourier Transforms (FFTs).
Large arrays are distributed and communications are handled under the hood by
MPI for Python (mpi4py). To distribute large arrays we are using a
`new and completely generic algorithm <https://arxiv.org/abs/1804.09536>`_
that allows for any index set of a multidimensional array to be distributed. We
can distribute just one index (a slab decomposition), two index sets (pencil
decomposition) or even more for higher-dimensional arrays.
mpi4py-fft comes with its own Python interface to the serial
`FFTW <http://www.fftw.org>`_ library. This interface can be used
much like `pyfftw <https://hgomersall.github.io/pyFFTW/>`_, and even for
real-to-real transforms, like discrete cosine or sine transforms.
Further documentation is found at `readthedocs <https://mpi4py-fft.readthedocs.io/en/latest/>`_.
Installation
------------
The mpi4py-fft package can be installed using::
pip install mpi4py-fft
or, to get the latest version from GitHub::
pip install git+https://github.com/mpi4py/mpi4py-fft@master
Install with conda from the coda-forge channel::
conda install -c conda-forge mpi4py-fft
or build it with conda build from the main source directory::
conda build -c conda-forge conf/
conda create --name mpi4py_fft mpi4py_fft --use-local
which will pull in the required dependencies from the conda-forge channel.
Note that mpi4py-fft depends on Python packages
* mpi4py
* numpy
* cython
and the serial C-library
* `FFTW <http://www.fftw.org>`_
Note in particular that *mpi4py* requires that you have a working
MPI installation, with the compiler wrapper *mpicc*, on your search path.
The FFTW header and libraries must also be available on the search path, and
we will build wrappers for any precision found of the FFTW libraries.
All of the above dependencies are available and will be downloaded through
the conda-forge channel if conda is used for installation. However, pip
will not help you with MPI or FFTW.
For IO you need to install either `h5py <https://www.h5py.org>`_ or
`netCDF4 <http://unidata.github.io/netcdf4-python/>`_ with support for
MPI. Both are available from the coda-forge channel through::
conda install -c conda-forge h5py=*=mpi* netcdf4=*=mpi*
Raw data
{
"_id": null,
"home_page": "https://bitbucket.org/mpi4py/mpi4py-fft",
"name": "mpi4py-fft",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "Python,FFTW,FFT,DCT,DST,MPI",
"author": "Lisandro Dalcin and Mikael Mortensen",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/45/68/9857b84a9947b2eafc1387b6d2cd6f4c3772ff0b857a046c349f64dadda9/mpi4py-fft-2.0.5.tar.gz",
"platform": null,
"description": "mpi4py-fft\n----------\n\n\n.. image:: https://dev.azure.com/mpi4py/mpi4py-fft/_apis/build/status/mpi4py.mpi4py-fft?branchName=master\n :target: https://dev.azure.com/mpi4py/mpi4py-fft\n\n.. image:: https://codecov.io/bb/mpi4py/mpi4py-fft/branch/master/graph/badge.svg\n :target: https://codecov.io/bb/mpi4py/mpi4py-fft\n\n.. image:: https://readthedocs.org/projects/mpi4py-fft/badge/?version=latest\n :target: https://mpi4py-fft.readthedocs.io/en/latest/?badge=latest\n :alt: Documentation Status\n\n.. image:: https://anaconda.org/conda-forge/mpi4py-fft/badges/downloads.svg\n :target: https://anaconda.org/conda-forge/mpi4py-fft\n :alt: Total downloads from conda-forge\n\n\nmpi4py-fft is a Python package for computing Fast Fourier Transforms (FFTs).\nLarge arrays are distributed and communications are handled under the hood by\nMPI for Python (mpi4py). To distribute large arrays we are using a\n`new and completely generic algorithm <https://arxiv.org/abs/1804.09536>`_\nthat allows for any index set of a multidimensional array to be distributed. We\ncan distribute just one index (a slab decomposition), two index sets (pencil\ndecomposition) or even more for higher-dimensional arrays.\n\nmpi4py-fft comes with its own Python interface to the serial\n`FFTW <http://www.fftw.org>`_ library. This interface can be used\nmuch like `pyfftw <https://hgomersall.github.io/pyFFTW/>`_, and even for\nreal-to-real transforms, like discrete cosine or sine transforms.\n\nFurther documentation is found at `readthedocs <https://mpi4py-fft.readthedocs.io/en/latest/>`_.\n\nInstallation\n------------\n\nThe mpi4py-fft package can be installed using::\n\n pip install mpi4py-fft\n\nor, to get the latest version from GitHub::\n\n pip install git+https://github.com/mpi4py/mpi4py-fft@master\n\nInstall with conda from the coda-forge channel::\n\n conda install -c conda-forge mpi4py-fft\n\nor build it with conda build from the main source directory::\n\n conda build -c conda-forge conf/\n conda create --name mpi4py_fft mpi4py_fft --use-local\n\nwhich will pull in the required dependencies from the conda-forge channel.\n\nNote that mpi4py-fft depends on Python packages\n\n * mpi4py\n * numpy\n * cython\n\nand the serial C-library\n\n * `FFTW <http://www.fftw.org>`_\n\nNote in particular that *mpi4py* requires that you have a working\nMPI installation, with the compiler wrapper *mpicc*, on your search path.\nThe FFTW header and libraries must also be available on the search path, and\nwe will build wrappers for any precision found of the FFTW libraries.\n\nAll of the above dependencies are available and will be downloaded through\nthe conda-forge channel if conda is used for installation. However, pip\nwill not help you with MPI or FFTW.\n\nFor IO you need to install either `h5py <https://www.h5py.org>`_ or\n`netCDF4 <http://unidata.github.io/netcdf4-python/>`_ with support for\nMPI. Both are available from the coda-forge channel through::\n\n conda install -c conda-forge h5py=*=mpi* netcdf4=*=mpi*\n\n\n\n",
"bugtrack_url": null,
"license": "",
"summary": "mpi4py-fft -- Parallel Fast Fourier Transforms (FFTs) using MPI for Python",
"version": "2.0.5",
"split_keywords": [
"python",
"fftw",
"fft",
"dct",
"dst",
"mpi"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "45689857b84a9947b2eafc1387b6d2cd6f4c3772ff0b857a046c349f64dadda9",
"md5": "abe3023a236bddb9e8304d8bfbcff10d",
"sha256": "7a8c7826f5c693a40beef1035f718f9cad0c4291934edc15d65bdcd13eac8a3b"
},
"downloads": -1,
"filename": "mpi4py-fft-2.0.5.tar.gz",
"has_sig": false,
"md5_digest": "abe3023a236bddb9e8304d8bfbcff10d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 36256,
"upload_time": "2023-04-26T08:43:58",
"upload_time_iso_8601": "2023-04-26T08:43:58.671460Z",
"url": "https://files.pythonhosted.org/packages/45/68/9857b84a9947b2eafc1387b6d2cd6f4c3772ff0b857a046c349f64dadda9/mpi4py-fft-2.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-04-26 08:43:58",
"github": false,
"gitlab": false,
"bitbucket": true,
"bitbucket_user": "mpi4py",
"bitbucket_project": "mpi4py-fft",
"lcname": "mpi4py-fft"
}
JSON