TSMC, the world leader in semiconductor manufacturing, is moving to production with NVIDIA's computational lithography platform, called cuLitho, to accelerate manufacturing and push the limits of physics for the next generation of advanced semiconductor chips.
Computational lithography, a critical step in chip manufacturing involving the transfer of circuitry onto silicon, has traditionally been a bottleneck in bringing new technology nodes to market. It is the most compute-intensive workload in the entire semiconductor design and manufacturing process, consuming tens of billions of hours per year on CPUs in the leading-edge foundries.
NVIDIA's cuLitho platform brings accelerated computing to this field, potentially transforming the industry. According to NVIDIA, 350 NVIDIA H100 Tensor Core GPU-based systems can now replace 40,000 CPU systems, accelerating production time, while reducing costs, space and power.
Dr. C.C. Wei, CEO of TSMC, highlighted the benefits of this collaboration at the GTC conference earlier this year: "Our work with NVIDIA to integrate GPU-accelerated computing in the TSMC workflow has resulted in great leaps in performance, dramatic throughput improvement, shortened cycle time and reduced power requirements."
NVIDIA has also developed algorithms to apply generative AI to enhance the cuLitho platform. This new generative AI workflow has been shown to deliver an additional 2x speedup on top of the accelerated processes enabled through cuLitho.
The application of generative AI enables creation of a near-perfect inverse mask or inverse solution to account for diffraction of light involved in computational lithography. The final mask is then derived by traditional and physically rigorous methods, speeding up the overall optical proximity correction process by 2x.
This advancement in computational lithography is expected to accelerate the creation of every single mask in the fab, which speeds the total cycle time for developing a new technology node. More importantly, it makes possible new calculations that were previously impractical due to computational limitations.
As current production processes are nearing the limits of what physics makes possible, this collaboration aims to enable the development of next-generation chip technology.