I-GCN: A Graph Convolutional Network Accelerator with Runtime Locality Enhancement through Islandization

Conference · Sat Oct 16 04:00:00 EDT 2021

DOI:https://doi.org/10.1145/3466752.3480113· OSTI ID:1832995

Geng, Tong ^[1]; Wu, Chunshu ^[2]; Zhang, Yongan ^[3]; Tan, Cheng ^[1]; Xie, Chenhao ^[1]; You, Haoran ^[3]; Herbordt, Martin ^[2]; Lin, Yingyan ^[3]; Li, Ang ^[1]

---

1. BATTELLE (PACIFIC NW LAB)
2. Boston University
3. Rice University

In this paper, we propose a novel hardware accelerator for GCN inference called I-GCN that significantly improves data locality and reduces unnecessary computation through a new online graph restructuring algorithm we refer to as islandization. The proposed algorithm finds clusters of nodes with strong internal but weak external connections. The islandization process yields two major benefits. First, by processing islands rather than individual nodes, there is better on-chip data reuse and fewer off-chip memory accesses. Second, there is less redundant computation as aggregation for common/shared neighbors in an island can be reused. The parallel search, identification, and leverage of graph islands are all handled purely in hardware at runtime working in an incremental pipelined manner. This is done without any preprocessing of the graph data or adjustment of the GCN model structure.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1832995
• Report Number(s): PNNL-SA-161514
• Country of Publication: United States
• Language: English