Presented by Mark Ebersole, a trainer at NVIDIA.
For most of the existence of Python, the idea of running actual performance optimized or production code natively in Python has been un-heard of. That is until Continuum Analytics introduced their Anaconda Accelerate product. Not only does it allow one to achieve speeds close to, if not equal to, native C/C++/Fortran while staying in Python; it allows you to fully utilize the awesome massively parallel power of an NVIDIA GPU using CUDA Python. This talk will briefly cover how the Accelerate product allows you to run performant code from Python on the CPU. We'll then touch on the "Why?" of GPU Computing, and dig into you can use the Accelerate software stack to program for an NVIDIA GPU in Python either directly with CUDA Python, or letting the Python SW do the parallelization for you.
Hope you can make it!