CUDACasts Episode #11: GPU Libraries for CUDA Python

Technical Blogs & Events Technical Blog
1

Originally published at: https://developer.nvidia.com/blog/cudacasts-episode-11-gpu-libraries-cuda-python/

In the previous episode of CUDACasts I introduced you to NumbaPro, the high-performance Python compiler from Continuum Analytics, and demonstrated how to accelerate simple Python functions on the GPU. Continuing the Python theme, today’s CUDACast demonstrates NumbaPro’s support for CUDA libraries. The optimized algorithms in GPU-accelerated libraries often provide the easiest way to accelerate applications. NumbaPro…

2

Hi Mark, Where can I obtain the python script(s) for this cast?

3

I took a peak at Github but I see no Python examples under CUDACasts and Mark Ebersole, only examples written in C.

4

Mark,
either there's an error in what you wrote or I'm missing something fundamental.
When you write d_next = step(....)
python should just overwrite the name d_next with whatever step returns. Did you mean to write
d_next[:] = step(....)
instead.
if not could you please explain why the way you wrote it works.
I'm confused!