ABSTRACT
Graph pattern mining (GPM) is getting increasingly important in recent years. Many graph pattern mining frameworks try to use universal primitives to deal with various graph pattern mining tasks. However, most of them suffer from unsatisfactory performance because of the exponential complexity of GPM. GPU is a new hardware with great parallelism, and many graph algorithms have achieved significant performance improvements on GPU. In this demo, we propose a graph pattern mining framework on GPU, called GAMMA. GAMMA proposes effective and flexible interfaces for users to implement their mining tasks conveniently. GPM has extensive intermediate results in parallel environments. We make full use of host memory to deal with large-scale graphs and extensive intermediate results. We also present several optimizations to process large graphs. GAMMA has great scalability and performance advantages compared with state-of-the-art graph mining works in experiments.
Supplemental Material
- Xuhao Chen, Roshan Dathathri, Gurbinder Gill, Loc Hoang, and Keshav Pingali. 2021. Sandslash: a two-level framework for efficient graph pattern mining. In Proceedings of the ACM International Conference on Supercomputing. 378--391.Google ScholarDigital Library
- Xuhao Chen, Roshan Dathathri, Gurbinder Gill, and Keshav Pingali. 2020. Pangolin: An Efficient and Flexible Graph Mining System on CPU and GPU. Proc. VLDB Endow. 13, 8 (2020), 1190--1205. https://doi.org/10.14778/3389133.3389137Google ScholarDigital Library
- Xuhao Chen, Tianhao Huang, Shuotao Xu, Thomas Bourgeat, Chanwoo Chung, and Arvind Arvind. 2021. FlexMiner: a pattern-aware accelerator for graph pattern mining. In 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA). IEEE, 581--594.Google ScholarDigital Library
- Kasra Jamshidi, Rakesh Mahadasa, and Keval Vora. 2020. Peregrine: a patternaware graph mining system. In EuroSys '20: Fifteenth EuroSys Conference 2020, Heraklion, Greece, April 27--30, 2020, Angelos Bilas, Kostas Magoutis, Evangelos P. Markatos, Dejan Kostic, and Margo I. Seltzer (Eds.). ACM, 13:1--13:16. https://doi.org/10.1145/3342195.3387548Google ScholarDigital Library
- Carlos HC Teixeira, Alexandre J Fonseca, Marco Serafini, Georgos Siganos, Mohammed J Zaki, and Ashraf Aboulnaga. 2015. Arabesque: a system for distributed graph mining. In Proceedings of the 25th Symposium on Operating Systems Principles. 425--440.Google ScholarDigital Library
- Li Zeng, Lei Zou, M Tamer Özsu, Lin Hu, and Fan Zhang. 2020. Gsi: Gpu-friendly subgraph isomorphism. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). IEEE, 1249--1260.Google ScholarCross Ref
Index Terms
- A GPU-based Graph Pattern Mining System
Recommendations
DecoMine: A Compilation-Based Graph Pattern Mining System with Pattern Decomposition
ASPLOS 2023: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1Graph pattern mining (GPM) is an important application that identifies structures from graphs. Despite the recent progress, the performance gap between the state-of-the-art GPM systems and an efficient algorithm—pattern decomposition—is still at least ...
Mining frequent graph patterns with differential privacy
KDD '13: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data miningDiscovering frequent graph patterns in a graph database offers valuable information in a variety of applications. However, if the graph dataset contains sensitive data of individuals such as mobile phone-call graphs and web-click graphs, releasing ...
Enhanced GPU-based distributed breadth first search
CF '15: Proceedings of the 12th ACM International Conference on Computing FrontiersThere is growing interest in studying large scale graphs having millions of vertices and billions of edges, up to the point that a specific benchmark, called Graph500, has been defined to measure the performance of graph algorithms on modern computing ...
Comments