NVIDIA Webinar
Python on the GPU: From Libraries to Kernels
Learn how to build high-performance solutions with NVIDIA.
Join us for an in-depth session with experts from NVIDIA and :probabl. where we’ll take a look at the changing landscape of CUDA Python and the ecosystem supporting GPU-accelerated computing. Probabl focuses on bringing advanced Python-based tooling and workflows to scientists, developers, and data teams.
The session will begin with a high-level overview of CUDA Python's design philosophy and roadmap. We’ll then share insights into nvmath and CUDA core compute libraries that form the foundation of high-performance computation. Attendees will learn how these core libraries integrate seamlessly with Python workflows, empowering data scientists, engineers, and developers to achieve new levels of performance and scalability.
Whether you're just starting with GPU programming or looking to deepen your understanding of CUDA's core capabilities, this webinar offers valuable takeaways and practical insights into the tools that drive GPU-accelerated innovation.
Learnings
In this webinar, we’ll cover the following topics:
- Session Introduction and high-level vision of CUDA Python
- nvmath, an open source library that bridges the gap between Python scientific community and NVIDIA CUDA-X™ math Libraries by reimagining Python’s performance-oriented APIs.
- CUDA core compute libraries, making CUDA C++ and Python more delightful.
- CUDA core, a fundamental processing unit designed for massive parallel computation.
