CUDA

What is CUDA?

The answer to this question is found at Nvidia's own What is CUDA? article:

CUDA is a parallel computing platform and programming model that makes using a GPU for general purpose computing simple and elegant. The developer still programs in the familiar C, C++, Fortran, or an ever expanding list of supported languages, and incorporates extensions of these languages in the form of a few basic keywords. These keywords let the developer express massive amounts of parallelism and direct the compiler to the portion of the application that maps to the GPU.

What is it Used For?

People have used GPUs to solve problems such as:

• Overcoming limitations in conventional fluid particle simulations
• Rolling their own 10-billion parameter neural networks
• Accelerating (non-graphics) applications in bioinformatics, data mining, and cryptography

Some Links

• CUDA Home page
• CUDA ZONE
• How to Teach CUDA
• Slidecasts
• A course at Udacity
• A cool article on deep learning
• The GPU Tecnology Conference (Browse the abstracts of the talks and papers!)