NVIDIA expands simulation tools for chip design and manufacturing

NVIDIA introduced cuPotential, a CUDA-X library for simulating atomic and molecular interactions, as semiconductor companies expand their use of AI across design, manufacturing and testing. Available in early access, the library lets developers add accelerated calculations to existing software and build AI agents that run and refine molecular simulations. NVIDIA reported an additional 2-3x acceleration in already GPU-optimized workflows during early-access testing, with Synopsys among the early adopters.

Partners are applying the broader software portfolio to engineering and production workflows. Synopsys reported early QuantumATK results showing a potential 30x speedup using cuEST. Lam Research plans to integrate the open-source NanoVDB library into SEMulator3D, with select wafer-etch modeling expected to accelerate by up to 30x. Applied Materials is using NVIDIA tools for materials discovery, process development and factory digital twins, enabling up to 35x faster chamber simulations.

Inspection and testing are also targets. A new NVIDIA NPP image-processing kernel incorporating KLA insights achieved performance 50x faster than earlier CPU versions. Teradyne reported approximately 85x faster probe-maintenance inference using GPU tools to identify degrading probes before they affect yield. Other deployments include AI-assisted production diagnostics, robotic simulation and inspection agents, supporting efforts to detect defects and validate changes before physical deployment.