Efficient Graph Data Access for Out-of-Memory GPU Streaming Graph Processing

Summary: Grapin enables out-of-memory GPU streaming graph processing by adapting incremental algorithms to GPU-friendly dependency handling, eliminating redundant accesses. Its vertex-centric hot-subgraph cache further reduces CPU–GPU transfers by 89% and achieves up to 96.9× speedup on billion-edge graphs. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 14194
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 10,950 | 24.88%
DOI: 10.14778/3749646.3749659

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Qiange Wang (National University of Singapore)
2. Yongze Yan (Northeastern University)
3. Hongshi Tan (National University of Singapore)
4. Cheng Chen (ByteDance)
5. Cheng Zhao (ByteDance)
6. Jiaming Tian (Northeastern University)
7. Jiaxin Jiang (National University of Singapore)
8. Xiaoliang Cong (ByteDance)
9. Yanfeng Zhang (Northeastern University)
10. Ge Yu (Northeastern University)
11. Weng-Fai Wong (National University of Singapore)
12. Bingsheng He (National University of Singapore)

BibTeX Citation

@article{wang_vldb25,
        title = {{Efficient Graph Data Access for Out-of-Memory GPU Streaming Graph Processing}},
        author = {Wang, Qiange and Yan, Yongze and Tan, Hongshi and Chen, Cheng and Zhao, Cheng and Tian, Jiaming and Jiang, Jiaxin and Cong, Xiaoliang and Zhang, Yanfeng and Yu, Ge and Wong, Weng-Fai and He, Bingsheng},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {11},
        pages = {3854--3867},
        doi = {10.14778/3749646.3749659},
        url = {https://doi.org/10.14778/3749646.3749659},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1,234	Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture	2021	VLDB	0.00011549432
2,060	Traversing Large Graphs on GPUs with Unified Memory	2020	VLDB	9.2454783e-05
3,027	Sortledton: a Universal, Transactional Graph Data Structure	2022	VLDB	7.8374092e-05
3,068	RisGraph: A Real-Time Streaming System for Evolving Graphs to Support Sub-millisecond Per-update Analysis at Millions Ops/s	2021	SIGMOD	7.7939351e-05
3,890	GaccO - A GPU-accelerated OLTP DBMS	2022	SIGMOD	7.0435206e-05
4,171	Accelerating Dynamic Graph Analytics on GPUs	2018	VLDB	6.8537202e-05
4,443	Incrementalizing Graph Algorithms	2021	SIGMOD	6.7004839e-05
5,480	EMOGI: Efficient Memory-access for Out-of-memory Graph-traversal in GPUs	2021	VLDB	6.2040237e-05
5,567	iTurboGraph: Scaling and Automating Incremental Graph Analytics	2021	SIGMOD	6.1709411e-05
6,203	Automating Incremental and Asynchronous Evaluation for Recursive Aggregate Data Processing	2020	SIGMOD	5.9447217e-05
9,967	Automating Incremental Graph Processing with Flexible Memoization	2021	VLDB	5.1869874e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,088	Fast Sparse Matrix-Vector Multiplication on GPUs: Implications for Graph Mining	2011	VLDB
2	11,087	Towards Sufficient GPU-accelerated Dynamic Graph Management: Survey and Experiment	2025	VLDB
3	5,597	Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses	2024	VLDB
4	1,911	Fast Iterative Graph Computation with Block Updates	2013	VLDB
5	1,234	Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture	2021	VLDB
6	3,740	GTS: A Fast and Scalable Graph Processing Method based on Streaming Topology to GPUs	2016	SIGMOD
7	10,564	gMatch: Fine-Grained and Hardware-Efficient Subgraph Matching on GPUs	2026	VLDB
8	4,157	GPU-based Graph Traversal on Compressed Graphs	2019	SIGMOD
9	5,075	CGgraph: An Ultra-fast Graph Processing System on Modern Commodity CPU-GPU Co-processor	2024	VLDB
10	4,171	Accelerating Dynamic Graph Analytics on GPUs	2018	VLDB