Graph Learning-Based Arithmetic Block Identification

Zhuolun He, Ziyi Wang, Chen Bai, Haoyu Yang, Bei Yu

20212021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)43 citationsDOI

Abstract

Arithmetic block identification in gate-level netlist is an essential procedure for malicious logic detection, functional verification, or macro-block optimization. We argue that existing methods suffer either scalability or performance issues. To address the problem, we propose a graph learning-based solution that promises to extract desired logic components from a complete design netlist. We further design a novel asynchronous bidirectional graph neural network (ABGNN) dedicated to representation learning on directed acyclic graphs. Experimental results on open-source RISC-V CPU designs demonstrate that our proposed solution significantly outperforms several state-of-the-art arithmetic block identification flows.

Topics & Concepts

NetlistComputer scienceScalabilityDirected acyclic graphTheoretical computer scienceBlock (permutation group theory)Logic synthesisGraphParallel computingArithmeticComputer architectureLogic gateAlgorithmEmbedded systemMathematicsDatabaseGeometryPhysical Unclonable Functions (PUFs) and Hardware SecurityAdversarial Robustness in Machine LearningIntegrated Circuits and Semiconductor Failure Analysis