Accelerating Science and Engineering With NVIDIA CUDA-X Libraries | NVIDIA GTC D.C.
NVIDIA CUDA-X Team
NVIDIA GTC 2025 · Session
This talk delves into **CUDA-X**, NVIDIA's comprehensive suite of libraries, frameworks, and AI models designed to accelerate every conceivable workload across diverse scientific and engineering domains. Building upon the foundational **CUDA** platform, which has married NVIDIA hardware to software for over two decades, **CUDA-X** represents the next logical evolution, aiming to empower millions of developers to build transformative applications. The presentation highlights NVIDIA's strategic shift from merely providing powerful GPUs to offering a rich software ecosystem that directly addresses complex computational challenges in fields ranging from industrial engineering and climate modeling to data science, computational biology, and quantum computing.
AI review
A sweeping NVIDIA GTC marketing keynote for CUDA-X that catalogs impressive-sounding numbers across a dozen domains without giving engineers enough to actually evaluate any of them. The performance claims are real and some of the underlying technology (cuEquivariance, CoreDiff, NVQLink) is genuinely interesting, but the talk is structured as a product showcase, not an engineering explanation. You leave knowing what NVIDIA wants you to feel about CUDA-X, not how any of it actually works.