Easy, Effective, Efficient: GPU Programming in Python with PyOpenCL and PyCUDA
This is an intensive short course on GPU computing via Python programming, to be lectured by the author of PyOpenCL and PyCUDA: Dr. Andreas Klöckner, Courant Institute of Mathematical Sciences, New York University. The course is free of charge (lunch included), open to anyone interested. Registration is required (either by email to email@example.com or using the sign-up link below) no later than August 22, 11AM.
Total number of guests outside of CBC: 4
Number of different nationalities represented: 6
Total number of speakers: 2
Total number of talks: 5
Programming GPUs is known to be fraught with some extra complexity compared to sequential programs. PyOpenCL is a package that joins scripting and GPU programming together. PyOpenCL can be used in a large number of roles, for example as a prototyping and exploration tool, to help with optimization, as a bridge to the GPU for existing legacy codes (in Fortran, C, or other languages), or, perhaps most excitingly, to support an unconventional hybrid way of writing high-performance codes. This short course teaches these roles and how to get the most out of PyOpenCL (and also PyCUDA).
For more information about the content of the short course, please read this document.
For travel information to Simula Research Laboratory, please view this link.
To sign up, please go to this site.
Aug 23, 2011
from 09:30 AM to 05:00 PM
|Where||Storstua, Simula Research Laboratory|
|Contact Name||Xing Cai|
Glenn T. Lines
Hans Petter Langtangen
|Add event to calendar||