Skip to content
Snippets Groups Projects
Commit 1a92620b authored by Andreas Klöckner's avatar Andreas Klöckner
Browse files

Add a readme with a link to the benchmarks

parent d5b7fbf7
No related branches found
No related tags found
1 merge request!81Add benchmarks for translations
sumpy: n-body kernels and translation operators
===============================================
.. image:: https://gitlab.tiker.net/inducer/sumpy/badges/master/pipeline.svg
:target: https://gitlab.tiker.net/inducer/sumpy/commits/master
.. image:: https://badge.fury.io/py/sumpy.png
:target: http://pypi.python.org/pypi/sumpy
Sumpy is mainly a 'scaffolding' package for Fast Multipole and quadrature methods.
If you're building one of those and need code generation for the required Multipole
and local expansions, come right on in. Together with boxtree, there is a full,
symbolically kernel-independent FMM implementation here.
Sumpy relies on
* `numpy <http://pypi.python.org/pypi/numpy>`_ for arrays
* `boxtree <http://pypi.python.org/pypi/boxtree>`_ for FMM tree building
* `sumpy <http://pypi.python.org/pypi/sumpy>`_ for expansions and analytical routines
* `loopy <http://pypi.python.org/pypi/loo.py>`_ for fast array operations
* `pytest <http://pypi.python.org/pypi/pytest>`_ for automated testing
and, indirectly,
* `PyOpenCL <http://pypi.python.org/pypi/pyopencl>`_ as computational infrastructure
PyOpenCL is likely the only package you'll have to install
by hand, all the others will be installed automatically.
Resources:
* `documentation <http://documen.tician.de/sumpy>`_
* `source code via git <http://github.com/inducer/sumpy>`_
If you can see inside the UIUC firewall, you may browse
`benchmark results <http://koelsch.cs.illinois.edu/benchmarks/asv/sumpy/>`_.
\ No newline at end of file
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment