Mega-KV: A Case for GPUs to Maximize the Throughput of In-Memory Key-Value Stores

Summary: Mega-KV rethinks in-memory key-value stores as GPU workloads, exploiting massive parallelism, bandwidth, and latency hiding for large working sets. Its dual-GPU prototype reaches 160+ Mops/s—1.4–2.8× faster than state-of-the-art CPU systems. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 11189
Venue: VLDB
Year: 2015
Pagerank: 8.5016595e-05
Overall Rank: 2,498 | 82.87%
DOI: 10.14778/2809974.2809982

Incoming Non-self Citations Over Time

Authors

1. Kai Zhang (University of Science and Technology Beijing)
2. Kaibo Wang (Ohio State University)
3. Yuan Yuan (Ohio State University)
4. Lei Guo (Ohio State University)
5. Rubao Lee (Ohio State University)
6. Xiaodong Zhang (Ohio State University)

BibTeX Citation

@article{zhang_vldb15,
        title = {{Mega-KV: A Case for GPUs to Maximize the Throughput of In-Memory Key-Value Stores}},
        author = {Zhang, Kai and Wang, Kaibo and Yuan, Yuan and Guo, Lei and Lee, Rubao and Zhang, Xiaodong},
        journal = {PVLDB},
        series = {{VLDB} '15},
        volume = {8},
        number = {11},
        pages = {1226--1237},
        doi = {10.14778/2809974.2809982},
        url = {https://doi.org/10.14778/2809974.2809982},
        year = {2015}
}

Incoming Citations (Sorted by Pagerank)

Showing 16 of 16 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
1,975	Morton Filters: Faster, Space-Efficient Cuckoo Filters via Biasing, Compression, and Decoupled Logical Sparsity	2018	VLDB	9.3645236e-05
2,457	BlueCache: A Scalable Distributed Flash-based Key-value Store	2017	VLDB	8.5515986e-05
2,848	GPL: A GPU-based Pipelined Query Processing Engine	2016	SIGMOD	8.0538815e-05
3,102	Efficient GPU-Accelerated Subgraph Matching	2023	SIGMOD	7.7568687e-05
4,603	The Art of Balance: A RateupDB Experience of Building a CPU/GPU Hybrid Database Product	2021	VLDB	6.6105578e-05
5,053	RTIndex: Exploiting Hardware-Accelerated GPU Raytracing for Database Indexing	2023	VLDB	6.3844953e-05
5,542	Put an Elephant into a Fridge: Optimizing Cache Efficiency for In-memory Key-value Stores	2020	VLDB	6.180117e-05
6,043	Mixer: Efficiently Understanding and Retrieving Visual Content at Web-scale	2021	VLDB	5.9966613e-05
7,263	Catalyst: Optimizing Cache Management for Large In-memory Key-value Systems	2023	VLDB	5.6611756e-05
9,376	H-Rocks: CPU-GPU accelerated Heterogeneous RocksDB on Persistent Memory	2025	SIGMOD	5.2755515e-05
9,439	GPH: An Efficient and Effective Perfect Hashing Scheme for GPU Architectures	2025	SIGMOD	5.2685863e-05
10,691	Flux: Unifying Heterogeneous Infrastructure for Alibaba AnalyticDB	2025	SIGMOD	5.093636e-05
11,087	Towards Sufficient GPU-accelerated Dynamic Graph Management: Survey and Experiment	2025	VLDB	5.093636e-05
11,224	X-TED: Massive Parallelization of Tree Edit Distance	2024	VLDB	5.093636e-05
11,332	High-Performance Spatial Data Analytics: Systematic R&D for Scale-Out and Scale-Up Solutions from the Past to Now	2024	VLDB	5.093636e-05
11,616	Rearchitecting In-Memory Object Stores for Low Latency	2022	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 8 of 8 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
105	Quickly Generating Billion-Record Synthetic Databases	1994	SIGMOD	0.00033877899
720	Anti-Caching: A New Approach to Database Management System Architecture	2013	VLDB	0.00014632914
823	The Yin and Yang of Processing Data Warehousing Queries on GPU Devices	2013	VLDB	0.00013792901
912	Hardware-Oblivious Parallelism for In-Memory Column-Stores	2013	VLDB	0.00013269804
2,504	Concurrent Analytical Query Processing with GPUs	2014	VLDB	8.4963369e-05
2,885	High-Throughput Transaction Executions on Graphics Processors	2011	VLDB	7.9969529e-05
7,105	Efficient In-memory Data Management: An Analysis	2014	VLDB	5.7008974e-05
8,580	Accelerating Pathology Image Data Cross-Comparison on CPU-GPU Hybrid Systems	2012	VLDB	5.4082911e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,993	Key-Value Storage Engines	2020	SIGMOD
2	2,566	Pump Up the Volume: Processing Large Data on GPUs with Fast Interconnects	2020	SIGMOD
3	4,779	LogKV: Exploiting Key-Value Stores for Event Log Processing	2013	CIDR
4	5,422	GPU Database Systems Characterization and Optimization	2024	VLDB
5	11,002	From FASTER to F2: Evolving Concurrent Key-Value Store Designs for Large Skewed Workloads	2025	VLDB
6	7,997	nKV in Action: Accelerating KV-Stores on Native Computational Storage with Near-Data Processing	2020	VLDB
7	4,888	Enabling Low Tail Latency on Multicore Key-Value Stores	2020	VLDB
8	5,542	Put an Elephant into a Fridge: Optimizing Cache Efficiency for In-memory Key-value Stores	2020	VLDB
9	10,341	Analysis and Evaluation of Using Microsecond-Latency Memory for In-Memory Indices and Caches in SSD-Based Key-Value Stores	2026	SIGMOD
10	9,506	FluidKV: Seamlessly Bridging the Gap between Indexing Performance and Memory-Footprint on Ultra-Fast Storage	2024	VLDB