Researchers at the University of Texas at Austin are leading a new initiative that brings artificial intelligence (AI) into the core of high-frequency RFIC and MMIC design. The effort, known as GENIE-RFIC (Generative ENgine for Intelligent and Expedited RFIC Design), aims to streamline the development of GaN-based monolithic microwave integrated circuits (MMICs) and CMOS radio-frequency integrated circuits (RFICs) by using AI to automate and optimize circuit creation based on performance targets.
Rather than following traditional, time-intensive workflows, the project leverages AI-driven inverse design techniques, which enable rapid generation of circuit topologies tailored to specific design requirements. To move these innovations beyond the lab, the team has spun out a startup named CircuitGenie, which will focus on commercial applications of the research.
Backed by a $9.6 million grant over 30 months from Natcast, the non-profit overseeing the U.S. National Semiconductor Technology Center (NSTC), the project is designed to cut development timelines and lower barriers to entry for RFIC design teams.
“Design productivity is a huge problem for RFICs; in most cases, it takes at least months to design a single chip,” said David Pan, the project’s principal investigator at the University of Texas. “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.”
Pan also noted that while AI tools will automate much of the early design process, a final verification step will remain essential.
However, “Golden simulation,” says Pan would still come at the end to finalise the work and make sure the chips perform as they’re intended.
The GENIE-RFIC project includes academic collaborators from Purdue University, George Washington University, UT Dallas, and Rice University, alongside industry experts at IBM, Cadence, and GlobalFoundries. Additional input, though not funded, is being contributed by companies and institutions such as the Texas Institute for Electronics, Qorvo, NVIDIA, Boeing, Texas Instruments, Analog Devices, and MediaTek.
Click here to learn more about the latest developments in AI.