NVIDIA Expands CUDA-X AI Tools For Semiconductor Manufacturing, Delivering 2–3x Faster Atom-Level Simulations And 30x Faster Chipmaking Simulations

• NVIDIA introduces cuPotential, a new NVIDIA CUDA-X library developers can use to build AI agents that simulate how atoms and molecules interact, accelerating already GPU-optimized workflows by an additional 2-3x in early-access testing.
• NanoVDB, an open source library for working with 3D data, accelerates chipmaking simulation for AI-defined fabs, helping Lam Research achieve 30x faster simulation.
• NVIDIA NPP, a library for processing images on GPUs, accelerates chipmaking inspection for AI-defined fabs, helping KLA accelerate inspection.
• Applied Materials, Cadence, KLA, Lam Research, Siemens, Synopsys and other semiconductor leaders are using NVIDIA’s accelerated computing and AI stack across chip design, manufacturing and testing, helping drive faster development, better yield and greater production capacity.

SAN FRANCISCO, Oct. 14, 2026 (GLOBE NEWSWIRE) -- SEMICON West -- NVIDIA today announced semiconductor leaders are adopting NVIDIA CUDA-X™ libraries — including the new NVIDIA cuPotential library, which developers can use to build AI agents that simulate how atoms and molecules interact — to advance AI-defined fabs.

AI-defined fabs are semiconductor factories where AI helps engineers optimize processes, solve production issues and improve production efficiency. As demand for advanced chips rises, such fabs must expand production while managing increasingly complex manufacturing processes. Engineers need new ways to model materials, analyze inspection data and test process changes in digital twins before applying them in production.

The expanded CUDA-X portfolio gives AI agents and engineering applications accelerated tools for semiconductor simulation, 3D data processing and image analysis, helping automate more engineering work across chip design and manufacturing so fabs can predict process behavior and improve yield.