Fast Gunrock Subgraph Matching (GSM) on GPUs
CoRR(2020)
摘要
In this paper, we propose a novel method, GSM (Gunrock Subgraph Matching), to compute graph matching (subgraph isomorphism) on GPUs. In contrast to previous approaches, GSM is BFS-based: possible matches are explored simultaneously in a breadth-first strategy and thus can be mapped onto GPUs in a massively parallel fashion. Our implementation on the Gunrock graph analytics framework follows a filtering-and-verification strategy. While previous work requires one-/two-step joining, we use one-step verification to decide the candidates in current frontier of nodes. Our implementation has a speedup up to 4x over previous GPU state-of-the-art implementation.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要