The contract is in support the Intelligent Design of Electronic Assets (IDEA) program, one of six new programs within DARPA’s Electronics Resurgence Initiative (ERI). These ERI investments are the next stage to create an automated electronics design capability for the aerospace/defence ecosystem and commercial needs.
The contract lasts four years, and during that time Cadence will be involved in the creation of a machine learning-driven Automatic Generation of Electronic Systems Through Intelligent Collaboration (MAGESTIC) research and development program. The program will introduce greater autonomy to the design process and develop design-intent-driven products. The Cadence-led team includes Carnegie Mellon University and NVIDIA.
The MAGESTIC program is intended to:
– Advance machine learning to develop algorithms to optimise performance
– Extend support for advanced CMOS process nodes
– Automate the routing and tuning of devices to improve reliability, circuit performance, and resilience
– Demonstrate improved power, performance and area (PPA) utilising machine learning, analytics, and optimisation
– Stage the introductions of the technology, allowing the system to learn from the users and teach users how to best achieve desired results.