A Real-time Adaptive Multi-stream GPU System For Online Approximate Nearest Neighborhood Search
2024 · Yiping Sun, Yang Shi, Jiaolong Du
Abstract
In recent years, Approximate Nearest Neighbor Search (ANNS) has played a pivotal role in modern search and recommendation systems, especially in emerging LLM applications like Retrieval-Augmented Generation. There is a growing exploration into harnessing the parallel computing capabilities of GPUs to meet the substantial demands of ANNS. However, existing systems primarily focus on offline scenarios, overlooking the distinct requirements of online applications that necessitate real-time insertion of new vectors. This limitation renders such systems inefficient for real-world scenarios. Moreover, previous architectures struggled to effectively support real-time insertion due to their reliance on serial execution streams. In this paper, we introduce a novel Real-Time Adaptive Multi-Stream GPU ANNS System (RTAMS-GANNS). Our architecture achieves its objectives through three key advancements: 1) We initially examined the real-time insertion mechanisms in existing GPU ANNS systems and disco
Authors
(none)
Tags
Stats
Related papers
- CAGRA: Highly Parallel Graph Construction And Approximate Nearest Neighbor Search For Gpus (2023)12.17
- Fusionanns: An Efficient CPU/GPU Cooperative Processing Architecture For Billion-scale Approximate Nearest Neighbor Search (2024)0.00
- GGNN: Graph-based GPU Nearest Neighbor Search (2019)13.39
- Breaking The Storage-compute Bottleneck In Billion-scale ANNS: A Gpu-driven Asynchronous I/O Framework (2025)0.00
- Parlayann: Scalable And Deterministic Parallel Graph-based Approximate Nearest Neighbor Search Algorithms (2023)10.35
- Freshdiskann: A Fast And Accurate Graph-based ANN Index For Streaming Similarity Search (2021)0.00
- Gpu-accelerated Multi-relational Parallel Graph Retrieval For Web-scale Recommendations (2025)0.00
- A Comprehensive Survey And Experimental Comparison Of Graph-based Approximate Nearest Neighbor Search (2021)17.35