NVIDIA and chipmakers apply CUDA-X libraries to AI-defined fabs

NVIDIA introduces cuPotential, a CUDA-X library for building AI agents that simulate how atoms and molecules interact, adding a 2-3x speedup on already GPU-optimized workflows in early-access testing.

Lam Research reports 30x faster chipmaking simulation using NanoVDB, and KLA accelerates inspection using NVIDIA NPP. Synopsys, Cadence, Applied Materials, Siemens and other semiconductor companies are adopting NVIDIA's accelerated computing and AI stack across chip design, manufacturing and testing.