TSMC Uses Nvidia AI Tools in Chipmaking, With 20%-50% Cost, Cycle-Time Gains
Nvidia said TSMC is using its accelerated computing and AI software in semiconductor design and manufacturing, adopting CUDA-X, Metropolis, TAO Toolkit and Omniverse. Nvidia said CUDA-X is being used across lithography, process simulation and fab operations, driving 20% to 50% gains in cost and cycle time.
Nvidia said the tools are intended to accelerate chip design, optimize fab operations and sharpen defect detection. The deployment extends into the factory that builds Nvidia's chips, with the aim of improving yield and throughput.
From the sources (4 posts)
@stocksavvyshay$NVDA says $TSM is using CUDA-X across lithography, process simulation & fab operations driving 20% to 50% cost & cycle-time gains. The company facing chip supply constraints is now selling the AI tools that help the factory buildi
@stockmktnewzNvidia $NVDA just posted this: “TSMC $TSM is using NVIDIA accelerated computing and AI to advance semiconductor design and manufacturing.”
@polymarketmoney$NVDA says $TSM is using their accelerated computing and AI to improve semiconductor design and manufacturing. The irony is Nvidia is helping the factory that builds its chips move faster.
@nvidianewsroomNews at #NVIDIAGTC: TSMC is using NVIDIA accelerated computing and AI to advance semiconductor design and manufacturing. The company is adopting NVIDIA CUDA-X, Metropolis, TAO Toolkit, and Omniverse to accelerate chip design, optimize fab