LightRW: FPGA Accelerated Graph Dynamic Random Walks
Summary: LightRW, an FPGA accelerator for Graph Dynamic Random Walks (GDRWs), enables fine-grained pipelines and memory-access optimizations to beat CPUs. Key ideas: parallel reservoir sampling, degree-aware on-chip caching, and a dynamic burst fetcher; up to 9.55x/9.10x speedups vs MetaPath/Node2vec; open-sourced. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Hongshi Tan (National University of Singapore)
- 2. Xinyu Chen (National University of Singapore)
- 3. Yao Chen (National University of Singapore)
- 4. Bingsheng He (National University of Singapore)
- 5. Weng-Fai Wong (National University of Singapore)
BibTeX Citation
@inproceedings{tan_sigmod23,
title = {{LightRW: FPGA Accelerated Graph Dynamic Random Walks}},
author = {Tan, Hongshi and Chen, Xinyu and Chen, Yao and He, Bingsheng and Wong, Weng-Fai},
series = {{SIGMOD} '23},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3588944},
url = {https://dl.acm.org/doi/10.1145/3588944},
year = {2023}
}
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 9,511 | DPDPU: Data Processing with DPUs | 2025 | CIDR | 5.25736e-05 |
| 11,228 | FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework | 2024 | VLDB | 5.093636e-05 |
| 11,236 | Improving Graph Compression for Efficient Resource-Constrained Graph Analytics | 2024 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,411 | word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data | 2020 | PODS | 0.00010852334 |
| 5,068 | Weighted Reservoir Sampling from Distributed Streams | 2019 | PODS | 6.3770298e-05 |
| 6,003 | ThunderRW: An In-Memory Graph Random Walk Engine | 2021 | VLDB | 6.0130964e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,157 | GPU-based Graph Traversal on Compressed Graphs | 2019 | SIGMOD |
| 2 | 11,693 | Approaching DRAM performance by using microsecond-latency flash memory for small-sized random read accesses: a new access method and its graph applications | 2021 | VLDB |
| 3 | 9,264 | ExtraV: Boosting Graph Processing Near Storage with a Coherent Accelerator | 2017 | VLDB |
| 4 | 10,252 | GraphRTX: Lighting the Way to Scalable Graph Analytics | 2026 | SIGMOD |
| 5 | 7,255 | Space-Efficient Random Walks on Streaming Graphs | 2023 | VLDB |
| 6 | 4,600 | LightNE: A Lightweight Graph Processing System for Network Embedding | 2021 | SIGMOD |
| 7 | 6,423 | Memory-Aware Framework for Efficient Second-Order Random Walk on Large Graphs | 2020 | SIGMOD |
| 8 | 7,201 | An I/O-Efficient Disk-based Graph System for Scalable Second-Order Random Walk of Large Graphs | 2022 | VLDB |
| 9 | 6,003 | ThunderRW: An In-Memory Graph Random Walk Engine | 2021 | VLDB |
| 10 | 11,228 | FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework | 2024 | VLDB |