High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU
Proceedings of the ACM on Management of Data · 04.12.2025 · 3 (6) · 1-27
DOI: 10.1145/3769799 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 05.12.2025. Verfasst von Haodi Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Approximate nearest neighbor search (ANNS) is broadly adopted in numerous scenarios. Real-world applications seek efficient ways to search billion-scale vectors in high throughput. On-SSD graph-based ANNS systems have the opportunity to achieve this goal, but the limited CPU computing power becomes a bottleneck. In this paper, we propose a GPU-centric, CPU-assisted ANNS architecture and design GustANN, a billion-scale graph-based vector search system for high throughput and cost-effectiveness. We achieve these goals with three techniques: (1) memory-efficient GPU kernels optimized to minimize the GPU memory usage in the graph search, which allows higher concurrency for GPU and SSD; (2) CPU-assisted transfer to address the PCIe bandwidth bottleneck on the GPU-side; (3) pivot search for inter-SSD load balancing. Compared to existing ANNS systems, GustANN achieves at least 2.50× higher throughput, and is 2.62× more cost-effective (measured in /QPS).
Förderung
- Beijing Natural Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Jiang, H., Guo, H., Xie, M., Shu, J., & Lu, Y. (2025). High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU. Proceedings of the ACM on Management of Data, 3(6), 1-27. https://doi.org/10.1145/3769799
Vancouver
Jiang H, Guo H, Xie M, Shu J, Lu Y. High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU. Proceedings of the ACM on Management of Data. 2025;3(6):1-27. doi:10.1145/3769799
BibTeX
@article{Jiang2025,
author = {Jiang, Haodi and Guo, Hao and Xie, Minhui and Shu, Jiwu and Lu, Youyou},
title = {High-Throughput, Cost-Effective Billion-Scale Vector Search with a Single GPU},
journal = {Proceedings of the ACM on Management of Data},
year = {2025},
volume = {3},
number = {6},
pages = {1--27},
doi = {10.1145/3769799}
}
EUVIMED