High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU
Summary: GustANN: a GPU-centric, CPU-assisted on-SSD graph-based ANNS that combines memory-efficient GPU kernels, CPU-managed PCIe transfers, and pivot-based inter-SSD load balancing to enable high-concurrency billion-scale vector search on a single GPU. Achieves ≥2.5× throughput and 2.62× better $/QPS versus prior ANNS systems. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Haodi Jiang (Tsinghua University)
- 2. Hao Guo (Tsinghua University)
- 3. Minhui Xie (Renmin University of China)
- 4. Jiwu Shu (Tsinghua University)
- 5. Youyou Lu (Tsinghua University)
BibTeX Citation
@inproceedings{jiang_sigmod26,
title = {{High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU}},
author = {Jiang, Haodi and Guo, Hao and Xie, Minhui and Shu, Jiwu and Lu, Youyou},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769799},
url = {https://dl.acm.org/doi/10.1145/3769799},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 7 of 7 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 93 | Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph | 2019 | VLDB | 0.00034701237 |
| 705 | HD-Index: Pushing the Scalability-Accuracy Boundary for Approximate kNN Search in High-Dimensional Spaces | 2018 | VLDB | 0.00014829964 |
| 1,357 | RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search | 2024 | SIGMOD | 0.00011043994 |
| 1,760 | Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment | 2024 | SIGMOD | 9.8157819e-05 |
| 2,519 | Similarity search in the blink of an eye with compressed indices | 2023 | VLDB | 8.4741476e-05 |
| 3,799 | SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search | 2025 | SIGMOD | 7.114484e-05 |
| 6,765 | AquaPipe: A Quality-Aware Pipeline for Knowledge Retrieval and Large Language Models | 2025 | SIGMOD | 5.7808599e-05 |
Previous
Page 1 / 1
Next