ZipFlow: a Compiler-based Framework to Unleash Compressed Data Movement for Modern GPUs

Summary: ZipFlow compiler-optimizes compression, PCIe transfer, and GPU decompression holistically, classifying codecs by parallelism and applying architecture-aware scheduling. It achieves 2.08× lower latency than nvCOMP and up to 3.14× over CPU engines. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID: h8726df5ff5486f56
Venue: VLDB
Year: 2026
Pagerank: 4.9605343e-05
Overall Rank: 10,975 | 26.44%
DOI: 10.14778/3827998.3828003
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

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

Authors

1. Gwangoo Yeo (Korea Advanced Institute of Science and Technology)
2. Zhiyang Shen (Tsinghua University)
3. Wei Cui (Microsoft)
4. Matteo Interlandi (Microsoft)
5. Rathijit Sen (Microsoft)
6. Bailu Ding (Microsoft)
7. Qi Chen (Microsoft)
8. Minsoo Rhu (Korea Advanced Institute of Science and Technology)

BibTeX Citation

@article{yeo_vldb26,
        title = {{ZipFlow: a Compiler-based Framework to Unleash Compressed Data Movement for Modern GPUs}},
        author = {Yeo, Gwangoo and Shen, Zhiyang and Cui, Wei and Interlandi, Matteo and Sen, Rathijit and Ding, Bailu and Chen, Qi and Rhu, Minsoo},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {12},
        pages = {3888--3901},
        doi = {10.14778/3827998.3828003},
        url = {https://doi.org/10.14778/3827998.3828003},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,993	TQP++: Bridging ML Compilers and Analytical Query Processing on GPUs	2026	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 27 of 27 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
610	Relational Joins on Graphics Processors	2008	SIGMOD	0.00015540189
748	The Yin and Yang of Processing Data Warehousing Queries on GPU Devices	2013	VLDB	0.00014258503
850	Hardware-Oblivious Parallelism for In-Memory Column-Stores	2013	VLDB	0.00013450864
1,228	A Study of the Fundamental Performance Characteristics of GPUs and CPUs for Database Analytics	2020	SIGMOD	0.00011425748
1,530	Pipelined Query Processing in Coprocessor Environments	2018	SIGMOD	0.00010318943
1,537	HippogriffDB: Balancing I/O and GPU Bandwidth in Big Data Analytics	2016	VLDB	0.00010296073
2,104	Database Compression on Graphics Processors	2010	VLDB	9.0262021e-05
2,239	BtrBlocks: Efficient Columnar Compression for Data Lakes	2023	SIGMOD	8.7753778e-05
2,464	Query Processing on Tensor Computation Runtimes	2022	VLDB	8.4081954e-05
2,485	A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs	2017	SIGMOD	8.3800709e-05
2,811	ALP: Adaptive Lossless floating-Point Compression	2023	SIGMOD	7.9587454e-05
2,886	Efficient Join Algorithms For Large Database Tables in a Multi-GPU Environment	2021	VLDB	7.8911081e-05
3,063	The FastLanes Compression Layout: Decoding >100 Billion Integers per Second with Scalar Code	2023	VLDB	7.6806166e-05
3,471	Tile-based Lightweight Integer Compression in GPU	2022	SIGMOD	7.258594e-05
3,828	Orchestrating Data Placement and Query Execution in Heterogeneous CPU-GPU DBMS	2022	VLDB	6.9779559e-05
3,968	Data-Parallel Query Processing on Non-Uniform Data	2020	VLDB	6.8770248e-05
3,982	TCUDB: Accelerating Database with Tensor Processors	2022	SIGMOD	6.8663329e-05
4,063	The Art of Balance: A RateupDB Experience of Building a CPU/GPU Hybrid Database Product	2021	VLDB	6.812902e-05
4,164	GPU Database Systems Characterization and Optimization	2024	VLDB	6.7560016e-05
4,650	Improving Execution Efficiency of Just-in-time Compilation based Query Processing on GPUs	2021	VLDB	6.471543e-05
4,872	GOLAP: A GPU-in-Data-Path Architecture for High-Speed OLAP	2024	SIGMOD	6.3582628e-05
5,425	Vortex: Overcoming Memory Capacity Limitations in GPU-Accelerated Large-Scale Data Analytics	2025	VLDB	6.121543e-05
5,721	Efficiently Processing Joins and Grouped Aggregations on GPUs	2025	SIGMOD	6.0008904e-05
6,393	GPU-accelerated data management under the test of time	2020	CIDR	5.7858902e-05
6,482	Output-sensitive Conjunctive Query Evaluation	2024	PODS	5.7529053e-05
8,007	Scaling GPU-Accelerated Databases beyond GPU Memory Size	2025	VLDB	5.3916546e-05
10,063	Share the Tensor Tea: How Databases can Leverage the Machine Learning Ecosystem	2022	VLDB	5.0751118e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,794	Scalable GPU Acceleration of Scalar Functions in Analytical Databases: Compilation, Benchmarking, and Optimization	2026	VLDB
2	6,393	GPU-accelerated data management under the test of time	2020	CIDR
3	1,537	HippogriffDB: Balancing I/O and GPU Bandwidth in Big Data Analytics	2016	VLDB
4	1,530	Pipelined Query Processing in Coprocessor Environments	2018	SIGMOD
5	4,226	GPU-based Graph Traversal on Compressed Graphs	2019	SIGMOD
6	10,399	G-CasDec: General Cascaded Decompression on GPUs	2027	SIGMOD
7	6,541	CompressGraph: Efficient Parallel Graph Analytics with Rule-Based Compression	2023	SIGMOD
8	2,104	Database Compression on Graphics Processors	2010	VLDB
9	9,905	GPU Acceleration of SQL Analytics on Compressed Data	2026	VLDB
10	3,471	Tile-based Lightweight Integer Compression in GPU	2022	SIGMOD