GES: High-Performance Graph Processing Engine and Service in Huawei
This paper presents the Graph Engine Service (GES), an advanced graph database management system characterized by its composable architecture and highly factorized query executor. This design enables GES to manage a substantial volume of concurrent queries with remarkable efficiency. GES currently holds the top position in the authoritative LDBC-SNB-DECLARATIVE benchmark rankings, showcasing its superior performance - exceeding the throughput of the second-place system by over three orders of magnitude, which provides its customers with exceptional cost-effectiveness and extraordinary user experiences.
Authors
- Jingwen Leng (ORCID: https://orcid.org/0000-0002-5660-5493)
- Wenliang Zhang (ORCID: https://orcid.org/0009-0007-1900-6487)
- Minyi Guo (ORCID: https://orcid.org/0000-0003-0034-2302)
- Shixuan Sun (ORCID: https://orcid.org/0000-0003-4060-9438)
- Sen Gao (ORCID: https://orcid.org/0009-0000-2151-9969)
- Chao Liu
- Chao Li (ORCID: https://orcid.org/0000-0001-6218-4659)
- Quan Chen (ORCID: https://orcid.org/0000-0001-5832-0347)
- Zhao Jianwen (ORCID: https://orcid.org/0000-0002-8929-0395)
- Chen Liang
- G. Chen
- Bo Ren
- Hao Zhang (ORCID: https://orcid.org/0000-0002-9192-4684)
- Chenyi Zhang (ORCID: https://orcid.org/0009-0003-9997-3901)
Institutions
- Shanghai Jiao Tong University (CN)
- Huawei Technologies (China) (CN)
Publication Details
- Published
- 2025-06-17
- DOI
- https://doi.org/10.1145/3722212.3724439
- Primary Topic
- Graph Theory and Algorithms
- Type
- article
- Field-Weighted Citation Impact
- 0.00