Cadence AI Autorouter May Transform the Landscape

Estimated reading time: 1 minute

Patrick Davis, product management director with Cadence Design Systems, discusses advancements in autorouting technology, including AI. He emphasizes a holistic approach that enhances placement and power distribution before routing. He points out that younger engineers seem more likely to embrace autorouting, while the veteran designers are still wary of giving up too much control. Will AI help autorouters finally gain industry-wide acceptance?

Andy Shaughnessy: Cadence has been updating and adding functionality to autorouters. What does Cadence offer regarding autorouting technology, and how does it help designers tackle complex and high-speed challenges?

Patrick Davis: While autorouting is a critical phase of the PCB design process, Cadence’s focus expands beyond routing to include the acceleration of adjacent functions that have a direct impact on quality of route. These include placement and power/ground distribution. By focusing on this broader challenge, it opens a broader solution set, allowing designers to converge on an optimized solution more quickly.

Our bleeding-edge customers, who design the most complex boards, spend as much time in placement as they do in routing. They know poor placement will inevitably result in additional layers, poor routing, and inefficient resource use. This is why our next-generation automation solution focused initially on placement. Feedback from our customers has been outstanding, confirming the critical role that excellent placement plays in simplifying subsequent routing tasks.

Once placement is completed, power plane definition is the next time sink, and is ripe for automation. Our tool also excels at power plane placement, allowing power to be efficiently managed alongside component placement, mirroring real-world designer workflows.

Finally, we reach routing, but with optimized placement and plane shapes, full board routing becomes viable. Our router, initially introduced in the IC packaging space, is now routing boards. We are seeing good results on designs of average complexity, with our current focus on addressing highly constrained, extremely dense boards.

Shaughnessy: Your autorouter announcement offered a roadmap for AI integration into your routers. What is the update on this integration and Cadence’s overall AI strategy?

To read the entire interview, which originally appeared in the June 2025 issue of Design007 Magazine, click here.