Covering Disruptive Technology Powering Business in The Digital Age

NVIDIA announced at GTC 2023 a breakthrough that brings accelerated computing to the field of computational lithography. This innovation will enable semiconductor leaders like ASML, TSMC and Synopsys to accelerate the design and manufacturing of next-generation chips. It is just in time as current production processes are nearing the limits of what physics makes possible.

The new NVIDIA cuLitho software library for computational lithography is being integrated by TSMC, the world’s leading foundry, as well as electronic design automation leader Synopsys into their software, manufacturing processes and systems for the latest-generation NVIDIA Hopper™ architecture GPUs. Equipment maker ASML is also working closely with NVIDIA on GPUs and cuLitho. The plan is to integrate support for GPUs into all of their computational lithography software products.

The advance will enable chips with tinier transistors and wires and accelerate time to market. It will also boost the energy efficiency of the massive data centres that run 24/7 to drive the manufacturing process.

“The chip industry is the foundation of nearly every other industry in the world,” said Jensen Huang, Founder of and CEO at NVIDIA. “With lithography at the limits of physics, NVIDIA’s introduction of cuLitho and collaboration with our partners TSMC, ASML and Synopsys allows fabs to increase throughput, reduce their carbon footprint and set the foundation for 2nm and beyond.”

Running on GPUs, cuLitho delivers a performance leap of up to 40x beyond current lithography, the process of creating patterns on a silicon wafer. This accelerates the massive computational workloads that currently consume tens of billions of CPU hours every year.

It also enables 500 NVIDIA DGX H100 systems to achieve the work of 40,000 CPU systems. It runs all parts of the computational lithography process in parallel, helping reduce power needs and potential environmental impact.

In the near term, fabs using cuLitho could help produce each day 3–5x more photomasks—the templates for a chip’s design. And it can do so using 9x less power than current configurations. A photomask that required two weeks can now be processed overnight.

Longer term, cuLitho will enable better design rules, higher density, higher yields and Artificial Intelligence (AI)-powered lithography.

Support from Industry Leaders

NVIDIA is working with key partners to smooth the speedy adoption of these new technologies.

“The cuLitho team has made admirable progress on speeding up computational lithography by moving expensive operations to GPU,” said C.C. Wei, CEO at TSMC. “This development opens up new possibilities for TSMC to deploy lithography solutions like inverse lithography technology and deep learning more broadly in chip manufacturing, making important contributions to the continuation of semiconductor scaling.”

“We are planning to integrate support for GPUs into all of our computational lithography software products,” said Peter Wennink, CEO at ASML. “Our collaboration with NVIDIA on GPUs and cuLitho should result in tremendous benefit to computational lithography, and therefore to semiconductor scaling. This will be especially true in the era of high NA extreme ultraviolet lithography.”

“Computational lithography, specifically optical proximity correction, or OPC, is pushing the boundaries of compute workloads for the most advanced chips,” said Aart de Geus, Chair and CEO at Synopsys. “By collaborating with our partner NVIDIA to run Synopsys OPC software on the cuLitho platform, we massively accelerated the performance from weeks to days! The team-up of our two leading companies continues to force amazing advances in the industry.”

Enabling Semiconductor Scaling

The cost of the computational time needed for the largest workloads in semi manufacturing has been outpacing Moore’s law. This is due to both the larger number of transistors in newer nodes and more stringent accuracy requirements. Future nodes require more detailed calculations. But not all of them can feasibly fit into the available computational bandwidth provided by the current platforms. This then slows the pace of innovation in semiconductors. A fab process change often requires an OPC revision, creating bottlenecks. cuLitho not only helps remove these bottlenecks, but it also makes possible novel solutions and innovative techniques. These include curvilinear masks, high NA EUV lithography and sub-atomic photoresist modelling needed for new technology nodes.

(0)(0)