ReGNN

Cong Liu, Haikun Liu, Hai Jin, Xiaofei Liao, Yu Zhang, Zhuohui Duan, Jiahong Xu, Huize Li

2022Proceedings of the 59th ACM/IEEE Design Automation Conference21 citationsDOI

Abstract

Graph Neural Networks (GNNs) have both graph processing and neural network computational features. Traditional graph accelerators and NN accelerators cannot meet these dual characteristics of GNN applications simultaneously. In this work, we propose a ReRAM-based processing-in-memory (PIM) architecture called ReGNN for GNN acceleration. ReGNN is composed of analog PIM (APIM) modules for accelerating matrix vector multiplication (MVM) operations, and digital PIM (DPIM) modules for accelerating non-MVM aggregation operations. To improve data parallelism, ReGNN maps data to aggregation sub-engines based on the degree of vertices and the dimension of feature vectors. Experimental results show that ReGNN speeds up GNN inference by 228x and 8.4x, and reduces energy consumption by 305.2x and 10.5x, compared with GPU and the ReRAM-based GNN accelerator ReGraphX, respectively.

Topics & Concepts

Computer scienceGraphParallel computingMatrix multiplicationEnergy consumptionHardware accelerationArtificial neural networkComputer architectureTheoretical computer scienceComputer hardwareArtificial intelligenceField-programmable gate arrayPhysicsBiologyQuantumQuantum mechanicsEcologyAdvanced Memory and Neural ComputingAdvanced Graph Neural NetworksFerroelectric and Negative Capacitance Devices