Back to All Open Science Grantees
Enhancing High-Level Scientific Computing Support in CuPy
To provide a series of GPU accelerated routines for signal processing and interpolation in CuPy to be a foundation for the research community.
CuPy is a Python library providing data structures and numerical algorithms for graphics processing units (GPUs). CuPy shares the same APIs as NumPy & SciPy to allow the use of GPUs at a minimal learning cost and without the need for in-depth knowledge of GPU programming models, keeping Python users within their comfort zone yet reaching significantly better performance. This proposal focuses on the development of new interpolation and signal processing modules for CuPy, as well as CuPy’s maintenance to support the latest platforms.