$30m for US projects to add AI into the RF design flow
Three teams in the US are developing AI techniques to boost the design of RF radio chips in a $30m programme.
Natcast, a nonprofit that operates the National Semiconductor Technology Centre (NSTC), is funding the first Artificial Intelligence Driven Radio Frequency Integrated Circuit Design Enablement (AIDRFIC) programme with projects from Keysight, Princeton and the University of Texas.
“Embracing AI for radio frequency design is paramount for maintaining the United States’ leadership in technological innovation,” said Deirdre Hanford, CEO of Natcast. “Leveraging AI not only accelerates our research capabilities but also ensures the US remains at the cutting edge of communication infrastructure. By investing in AI-driven RF solutions, we secure our competitive edge, bolster national security, and drive economic growth, affirming the U.S. as the leader in the global tech landscape.”
Teams come from Keysight Technologies, Princeton University, and the University of Texas at Austin and will be working over the next two years
“RFIC design is a complex, time-intensive process requiring expertise in electromagnetics and circuit optimization,” said Dr. Marcus Pan, AIDRFIC Program Manager at Natcast. “By exploring and investing in projects like these that leverage AI and ML technologies to revolutionize the RFIC design landscape, the U.S. can significantly accelerate development and improve design quality of leading-edge technologies that are essential for the evolving power and efficiency needs of broadband, beyond 5G and 6G, and next-gen RF hardware.”
The team from the University of Texas at Austin (above), is adding generative AI into the design process for CMOS and GaN microwave MMICs in the $9.6m GENIE-RFIC Generative ENgine for Intelligent and Expedited RFIC Design project
“Design productivity is a huge problem for RFICs; in most cases, it takes at least months to design a single chip,” said Prof David Pan at the Cockrell School of Engineering’s Chandra Family Department of Electrical and Computer Engineering and the project’s principal investigator. “Our goal is to significantly enhance design productivity by reducing development time and cost through an AI-assisted design flow, while also lowering the experience barrier for performing RFIC designs.”
The AI-driven tools will perform rapid “inverse” designs based on target specifications, optimizing circuit topologies and parameters.
Industry partners include IBM, Cadence, and GlobalFoundries. The researchers are developing a startup company, CircuitGenie, to commercialize technologies from this program. Several unfunded partners are contributing to the work, including Qorvo, Nvidia, Boeing, Texas Instruments, Analog Devices and MediaTek.
At Princeton, the IMAGINE project is developing Inverse Methods and Generative AI for Algorithmic and Non-intuitive Design Explorations in RFICs. This is rethinking the RFIC design process from the ground up. Leveraging AI and inverse design methodologies to build an end-to-end design pipeline that can rapidly move from specs to layout.
Keysight is leading an EDA industrial initiative to add AI-driven automation to the EDA design tool flow.
natcast.org/natcast-finalizes-first-nstc-rd-contracts
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
