FlowTune: Practical Multi-armed Bandits in Boolean Optimization

• Published in: 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD) pp. 1 - 9
• Main Author: Yu, Cunxi
• Format: Conference Proceeding
• Language: English
• Published: Association on Computer Machinery 02.11.2020
• Subjects: area optimization; Boolean functions; Boolean logic optimization; Boolean optimization; Conjuction Normal Form minimization; delays; design closure process; electronic design automation; field programmable gate arrays; generic end-to-end; Libraries; logic design; Logic gates; multi-stage multi-armed bandit framework; optimisation; Optimization; optimization problems; practical EDA toolflow integration; practical multiarmed bandits; Space exploration; static timing analysis; table lookup
• ISSN: 1558-2434
• DOI: 10.1145/3400302.3415615

Recent years have seen increasing employment of decision intelligence in electronic design automation (EDA), which aims to reduce the manual efforts and boost the design closure process in modern toolflows. However, existing approaches either require a large number of labeled data for training or are limited in practical EDA toolflow integration due to computation overhead. This paper presents a generic end-to-end and high-performance domain-specific, multi-stage multi-armed bandit framework for Boolean logic optimization. This framework addresses optimization problems on a) And-Inv-Graphs (# nodes), b) Conjunction Normal Form (CNF) minimization (# clauses) for Boolean Satisfiability, c) post static timing analysis (STA) delay and area optimization for standard-cell technology mapping, and d) FPGA technology mapping for 6-in LUT architectures. Moreover, the proposed framework has been integrated with ABC [1], Yosys [2], VTR [3], and industrial tools. The experimental results demonstrate that our framework outperforms both hand-crafted flows [1] and ML explored flows [4], [5] in quality of results, and is orders of magnitude faster compared to ML-based approaches [4], [5].