EUVIMEDEUVIMED entdecken
Crossref

SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search

Yuchen Peng, Dingyu Yang, Zhongle Xie, Ji Sun, Lidan Shou, Ke Chen, Gang Chen

Proceedings of the VLDB Endowment · 01.01.2026 · 19 (5) · 1074-1087

DOI: 10.14778/3796195.3796216 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 05.05.2026. Verfasst von Yuchen Peng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Approximate Nearest Neighbor Search (ANNS) underpins modern applications such as information retrieval and recommendation. With the rapid growth of vector data, efficient indexing for real-time vector search has become rudimentary. Existing CPU-based solutions support updates but suffer from low throughput, while GPU-accelerated systems deliver high performance but face challenges with dynamic updates and limited GPU memory, resulting in a critical performance gap for continuous, large-scale vector search requiring both accuracy and speed. In this paper, we present SVFusion, a GPU-CPU-disk collaborative framework for real-time vector search that bridges sophisticated GPU computation with online updates. SVFusion leverages a hierarchical vector index architecture that employs CPU-GPU co-processing, along with a workload-aware vector caching mechanism to maximize the efficiency of limited GPU memory. It further enhances performance through real-time coordination with CUDA multi-stream optimization and adaptive resource management, along with concurrency control that ensures data consistency under interleaved queries and updates. Empirical results demonstrate that SVFusion achieves significant improvements in query latency and throughput, exhibiting a 20.9× higher throughput on average and 1.3× to 50.7× lower latency compared to baseline methods, while maintaining high recall for large-scale datasets under various streaming workloads.

Zitieren

APA

Peng, Y., Yang, D., Xie, Z., Sun, J., Shou, L., Chen, K., & Chen, G. (2026). SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search. Proceedings of the VLDB Endowment, 19(5), 1074-1087. https://doi.org/10.14778/3796195.3796216

Vancouver

Peng Y, Yang D, Xie Z, Sun J, Shou L, Chen K, et al. SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search. Proceedings of the VLDB Endowment. 2026;19(5):1074-1087. doi:10.14778/3796195.3796216

BibTeX
@article{Peng2026,
  author = {Peng, Yuchen and Yang, Dingyu and Xie, Zhongle and Sun, Ji and Shou, Lidan and Chen, Ke and Chen, Gang},
  title = {SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {5},
  pages = {1074--1087},
  doi = {10.14778/3796195.3796216}
}
Kostenlos starten →