GCIM: Toward Efficient Processing of Graph Convolutional Networks in 3D-Stacked Memory

• Published in: IEEE transactions on computer-aided design of integrated circuits and systems Vol. 41; no. 11; pp. 3579 - 3590
• Main Authors: Chen, Jiaxian, Lin, Yiquan, Sun, Kaoyi, Chen, Jiexin, Ma, Chenlin, Mao, Rui, Wang, Yi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3D-stacked memory; accelerator; Algorithms; Artificial neural networks; Co-design; Common Information Model (computing); computation-in-memory (CIM); Computer architecture; Computer memory; Data processing; graph convolutional networks (GCNs); Hardware; Machine learning; Memory management; Network latency; Neural networks; Software; Software algorithms; Software design; Structured data; Systems architecture
• ISSN: 0278-0070; 1937-4151
• DOI: 10.1109/TCAD.2022.3198320

Graph convolutional networks (GCNs) have become a powerful deep learning approach for graph-structured data. Different from traditional neural networks such as convolutional neural networks, GCNs handle irregular input graph data, and GCNs are both computation-bound and memory-bound. How to efficiently utilize the underlying computation and memory resource becomes a critical issue. The emerging 3D-stacked computation-in-memory (CIM) architecture can reduce the data movement between computing logic and memory, thereby presenting a promising solution for the processing of GCNs. An unsolved key challenge is how to allocate GCNs to take advantage of fast near-data processing of the 3D-stacked CIM architecture. This article presents GCIM, a software-hardware co-design approach to exploit the efficient processing of GCNs on the CIM architecture. At the level of hardware design, GCIM integrates lightweight computing units near memory banks to fully exploit bank-level bandwidth and parallelism. At the level of software design, a locality-aware data mapping algorithm is proposed to partition the input graph and achieve workload balancing. GCIM is evaluated through a set of representative GCN models and standard graph datasets. The experimental results show that GCIM can significantly reduce the processing latency and data movement overhead compared with representative schemes.