BOiLS: Bayesian Optimisation for Logic Synthesis
Antoine Grosnit1,a, Cedric Malherbe1,b, Rasul Tutunov1,c, Xingchen Wan2, Jun Wang3,d and Haitham Bou Ammar3,e
1Huawei Noah's Ark Lab
aantoine.grosnit@huawei.com
bcedric.malherbe@huawei.com
crasul.tutunov@huawei.com
2Huawei Noah's Ark Lab University of Oxford
xingchen.wan@huawei.com
3Huawei Noah'3s Ark Lab University College London
dw.j@huawei.com
ehaitham.ammar@huawei.com
ABSTRACT
Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces. While expertdesigned operations aid in uncovering effective sequences, the increase in complexity of logic circuits favours automated procedures. To enable efficient and scalable solvers, we propose BOiLS, the first algorithm adapting Bayesian optimisation to navigate the space of synthesis operations. BOiLS requires no human intervention and trades-off exploration versus exploitation through novel Gaussian process kernels and trust-region constrained acquisitions. In a set of experiments on EPFL benchmarks, we demonstrate BOiLS’s superior performance compared to state-ofthe- art in terms of both sample efficiency and QoR values.
Keywords: Logic synthesis, Bayesian Optimisation.
