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
- 2. Hao Guo
- 3. Minhui Xie
- 4. Jiwu Shu
- 5. Youyou Lu
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 |
|---|---|---|---|---|
| 212 | Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph | 2019 | VLDB | 0.00033913475 |
| 1,010 | HD-Index: Pushing the Scalability-Accuracy Boundary for Approximate kNN Search in High-Dimensional Spaces | 2018 | VLDB | 0.00014652858 |
| 2,324 | RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search | 2024 | SIGMOD | 9.0326444e-05 |
| 2,690 | Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment | 2024 | SIGMOD | 8.293714e-05 |
| 3,609 | Similarity search in the blink of an eye with compressed indices | 2023 | VLDB | 6.9215236e-05 |
| 5,184 | SymphonyQG: Towards Symphonious Integration of Quantization and Graph for Approximate Nearest Neighbor Search | 2025 | SIGMOD | 5.6406991e-05 |
| 7,193 | AquaPipe: A Quality-Aware Pipeline for Knowledge Retrieval and Large Language Models | 2025 | SIGMOD | 4.8039257e-05 |
Previous
Page 1 / 1
Next