Towards efficient allocation of graph convolutional networks on hybrid computation-in-memory architecture  

作　　者：Jiaxian CHEN Guanquan LIN Jiexin CHEN Yi WANG 

机构地区：[1]College of Computer Science and Software Engineering,Shenzhen University,Shenzhen 518060,China

出　　处：《Science China(Information Sciences)》2021年第6期108-121,共14页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China (Grant No. 61972259);Guangdong Basic and Applied Basic Research Foundation (Grant Nos. 2019B151502055, 2017B030314073, 2018B030325002)。

摘　　要：Graph convolutional networks(GCNs) have been applied successfully in social networks and recommendation systems to analyze graph data. Unlike conventional neural networks, GCNs introduce an aggregation phase, which is both computation-and memory-intensive. This phase aggregates features from the neighboring vertices in the graph, which incurs significant amounts of irregular data and memory access.The emerging computation-in-memory(CIM) architecture presents a promising solution to alleviate the problem of irregular accesses and provide fast near-data processing for GCN applications by integrating both three-dimensional stacked CIM and general-purpose processing units in the system. This paper presents Graph-CIM, which exploits the hybrid CIM architecture to determine the allocation of GCN applications.Graph-CIM models the GCN application process as a directed acyclic graph(DAG) and allocates tasks on the hybrid CIM architecture. It achieves fine-grained graph partitioning to capture the irregular characteristics of the aggregation phase of GCN applications. We use a set of representative GCN models and standard graph datasets to evaluate the effectiveness of Graph-CIM. The experimental results show that Graph-CIM can significantly reduce the processing latency and data-movement overhead compared with the representative schemes.

关 键 词：computation-in-memory graph convolutional networks hybrid architecture scheduling inference ACCELERATOR 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]