Talk Experiences making CPU-bound tasks run much faster

Abstract

In this talk I'll look at the ways we can make a single computer run Python code much faster using the following tools:
* numpy
* NumExpr
* Cython
* ShedkSkin (Python to C++ compiler)
* PyPy
* the multiprocessing module

This talk will be an updated version of the tutorial I'm running on the same subject at EuroPython 2011:
http://ep2011.europython.eu/conference/talks/experiences-making-cpu-bound-tasks-run-much-faster

I'm a commercial Python researcher working on artificial intelligence and high performance computing problems. I use Python as my main programming language and making my code run faster is of primary importance. In this talk I'll boil down my lessons for practical approaches to making your CPU-bound code run faster.

Language: English

Attachments
tagged by
no related entity