Tweet
Tweet

Slide 1

Slide 1 text

We love pandas, but it can be slow

Slide 2

Slide 2 text

Accelerated pandas cudf.pandas: the zero code change GPU accelerator for pandas built on cuDF

Slide 3

Slide 3 text

Zero code change Your existing code, but faster

Slide 4

Slide 4 text

Accelerated NetworkX Zero code change acceleration for NetworkX, powered by cuGraph • Zero code change GPU-acceleration for NetworkX code • Accelerates algorithms up to 600x, based on algorithm and graph size • Support for 60 popular graph algorithms and growing • Fallback to using CPU NetworkX for any unsupported algorithms NetworkX 3.2, CPU: Intel(R) Xeon(R) Platinum 8480CL 2TB, GPU: NVIDIA H100 80GB pip install nx-cugraph-cu12 --extra-index-url https://pypi.nvidia.com conda install -c rapidsai -c conda-forge -c nvidia nx-cugraph

Slide 5

Slide 5 text

https://nvda.ws/45vQqdr