A Real-Time Adaptive Multi-Stream GPU System for Online Approximate Nearest Neighborhood Search

TL;DR

This paper presents RTAMS-GANNS, a GPU-based system enabling real-time, parallel approximate nearest neighbor search with dynamic vector insertion, significantly improving latency and supporting large-scale industrial applications.

Contribution

The paper introduces a novel multi-stream GPU architecture with dynamic insertion algorithms, addressing real-time constraints previously unmet by existing systems.

Findings

Reduces latency by up to 80% across datasets.

Supports real-time insertion without blocking execution.

Successfully deployed in large-scale industrial systems.

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 discovered their reliance on repetitive copying and memory allocation, which significantly hinders real-time effectiveness on GPUs. As a solution, we introduce a dynamic vector insertion algorithm based on memory blocks, which includes in-place rearrangement. 2) To enable real-time vector insertion in parallel, we introduce a multi-stream parallel execution mode, which differs from existing systems that operate serially within a single stream. Our system utilizes a dynamic resource pool, allowing multiple streams to execute concurrently without additional execution blocking. 3) Through extensive experiments and comparisons, our approach effectively handles varying QPS levels across different datasets, reducing latency by up to 40%-80%. The proposed system has also been deployed in real-world industrial search and recommendation systems, serving hundreds of millions of users daily, and has achieved good results.