After clicking “Watch Now” you will be prompted to login or join.
CuPy Overview: NumPy Syntax Computation with Advanced CUDA Features
Crissman Loomis, Preferred Networks | Emilio Castillo, Preferred Networks
GTC 2020
We'll introduce CuPy, describing the advantages of the library and how it is cleanly exposing in Python multiple CUDA state-of-the art libraries such as cuTENSOR or cuDNN. Discover the CuPy advantages and how they can use it to experience performance gains in their NumPy codes without any major changes.