Accelerating Stream Processing Engines via Hardware Offloading

Summary: FlexStream offloads re-partitioning to hardware and adopts a coupled network-executor model to saturate NIC bandwidth and rethink SPE parallelization. With a lock-free state backend and fast migration it achieves 1.95–3.35× throughput and much lower latency spikes and migration time versus prior SPEs. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID: h15f26678409b9986
Venue: SIGMOD
Year: 2026
Pagerank: 4.9769913e-05
Overall Rank: 10,552 | 29.08%
DOI: 10.1145/3769754
PDF: Download (CC BY 4.0)

Incoming Non-self Citations Over Time

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

Authors

1. Zhengyan Guo (Tsinghua University)
2. Mingxing Zhang (Tsinghua University)
3. Yingdi Shan (Tsinghua University)
4. Kang Chen (Tsinghua University)
5. Jinlei Jiang (Tsinghua University)
6. Yongwei Wu (Tsinghua University)

BibTeX Citation

@inproceedings{guo_sigmod26,
        title = {{Accelerating Stream Processing Engines via Hardware Offloading}},
        author = {Guo, Zhengyan and Zhang, Mingxing and Shan, Yingdi and Chen, Kang and Jiang, Jinlei and Wu, Yongwei},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3769754},
        url = {https://dl.acm.org/doi/10.1145/3769754},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 15 of 15 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
215	Morsel-Driven Parallelism: A NUMA-Aware Query Evaluation Framework for the Many-Core Age	2014	SIGMOD	0.00024589307
231	Storm @Twitter	2014	SIGMOD	0.00023830094
606	Twitter Heron: Stream Processing at Scale	2015	SIGMOD	0.00015627966
970	Integrating Scale Out and Fault Tolerance in Stream Processing using Operator State Management	2013	SIGMOD	0.00012776109
1,236	Dhalion: Self-Regulating Stream Processing in Heron	2017	VLDB	0.00011400483
3,398	Megaphone: Latency-conscious state migration for distributed streaming dataflows	2019	VLDB	7.3318754e-05
3,923	Analyzing Efficient Stream Processing on Modern Hardware	2019	VLDB	6.919667e-05
4,110	Rhino: Efficient Management of Very Large Distributed State for Stream Processing Engines	2020	SIGMOD	6.797656e-05
4,919	LightSaber: Efficient Window Aggregation on Multi-core Processors	2020	SIGMOD	6.3519157e-05
5,331	BriskStream: Scaling Data Stream Processing on Shared-Memory Multicore Architectures	2019	SIGMOD	6.1770377e-05
6,444	Grizzly: Efficient Stream Processing Through Adaptive Query Compilation	2020	SIGMOD	5.7807677e-05
6,626	Watermarks in Stream Processing Systems: Semantics and Comparative Analysis of Apache Flink and Google Cloud Dataflow	2021	VLDB	5.7288333e-05
7,980	Rethinking Stateful Stream Processing with RDMA	2022	SIGMOD	5.4120499e-05
9,482	Elasticutor: Rapid Elasticity for Realtime Stateful Stream Processing	2019	SIGMOD	5.1687151e-05
9,817	Scabbard: Single-Node Fault-Tolerant Stream Processing	2022	VLDB	5.1233734e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,531	Low-Latency Adaptive Distributed Stream Join System Based on a Flexible Join Model	2024	SIGMOD
2	4,919	LightSaber: Efficient Window Aggregation on Multi-core Processors	2020	SIGMOD
3	7,995	From a Stream of Relational Queries to Distributed Stream Processing	2010	VLDB
4	9,648	Providing Resiliency to Load Variations in Distributed Stream Processing	2006	VLDB
5	8,426	Demonstrating PDSP-Bench: A Benchmarking System for Parallel and Distributed Stream Processing	2025	SIGMOD
6	7,980	Rethinking Stateful Stream Processing with RDMA	2022	SIGMOD
7	2,446	Design, Implementation, and Evaluation of the Linear Road Benchmark on the Stream Processing Core	2006	SIGMOD
8	9,482	Elasticutor: Rapid Elasticity for Realtime Stateful Stream Processing	2019	SIGMOD
9	6,543	A Holistic View of Stream Partitioning Costs	2017	VLDB
10	3,923	Analyzing Efficient Stream Processing on Modern Hardware	2019	VLDB