Search papers, labs, and topics across Lattice.
This paper introduces SynAct, an adaptive reasoning-acting large language model agent designed for optimizing logic synthesis by dynamically diagnosing synthesis reports and issuing targeted commands based on the current circuit state and historical data. The significance lies in its ability to outperform traditional methods by reducing worst negative slack (WNS) to just 27% of that achieved through bootstrap synthesis, demonstrating a substantial improvement in timing optimization. By integrating real-time feedback into the synthesis process, SynAct enhances both the efficiency and effectiveness of circuit design optimization.
SynAct slashes worst negative slack to 27% of bootstrap synthesis, revolutionizing timing optimization in logic synthesis.
Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis.
