Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Jul 10, 2009
The traditional way of computing is running out of steam because CPUs are no longer increasing in speed. It is critical that the industry move to parallel computing on multi-core computing architectures to continue to advance computational research. Students at University of Illinois at Urbana-Champaign are being taught parallel programming on the CUDA architecture to reap the real benefits of parallelism. As Dr. Wen-mei Hwu discusses, the CUDA programming environment is a simple solution to a daunting, complex problem.