GraphMatch: Subgraph Query Processing on FPGAs

• DOI: 10.48550/arxiv.2402.17559
• Publication Date: 2024-02-27
• Authors: Jonas Dann; Tobias Götz; Daniel Ritter; Jana Giceva; Holger Fröning

Efficiently finding subgraph embeddings in large graphs is crucial for many application areas like biology and social network analysis. Set intersections are the predominant most challenging aspect of current join-based query processing systems CPUs. Previous work has shown viability utilizing FPGAs acceleration graph join processing. In this work, we propose GraphMatch, first genearl-purpose stand-alone accelerator based on worst-case optimal joins (WCOJ) that fully designed modern, field programmable gate array (FPGA) hardware. For efficient various data sets patterns, it leverages a novel set intersection approach, called AllCompare, tailor-made FPGAs. We show approach efficiently solves multi-set processing, superior to CPU-based approaches. Overall, GraphMatch achieves speedup over 2.68x 5.16x, compared state-of-the-art GraphFlow RapidMatch, respectively.