Computational Lithography to Enable Faster AI Development

As applications for artificial intelligence are developing rapidly, the need for ever higher computational power to train massive datasets for AI puts a premium on chipmaking technology. Conventional photolithography is increasingly difficult as gate density increases on modern semiconductors, and single digit nanometer devices are more time-consuming and difficult to fabricate. Nvidia has developed a software package in collaboration with ASML, Synopsys and TSMC which is designed to run with Nvidia graphics processor units in a system that promises to eventually produce an order of magnitude faster wafer production. 2 nm devices are under study, which may represent the physics limit to PLC development with photolithography technology.  * * *Want to watch this podcast as a video? This Week in Engineering is available on engineering.com TV along with all of our other shows such as End of the Line, Designing the Future, Manufacturing the Future, and the Engineering Roundtable.