A GPU-Accelerated Framework for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search

TL;DR

Garfield is a GPU-accelerated framework for multi-attribute range filtered approximate nearest neighbor search that significantly improves throughput and reduces index size compared to existing CPU-based solutions.

Contribution

It introduces the GMG index and a hardware-aware execution pipeline to overcome bottlenecks in RFANNS, enabling efficient GPU-based indexing and querying.

Findings

Reduces index size by 4.4x

Achieves 119.8x higher throughput than state-of-the-art methods

Supports datasets exceeding GPU memory with out-of-core processing

Abstract

Range-filtered approximate nearest neighbor search (RFANNS) is increasingly critical for modern vector databases. However, existing solutions suffer from severe index inflation and construction overhead. Furthermore, they rely exclusively on CPUs for the heavy indexing and query processing, significantly restricting the throughput due to the limited memory bandwidth and parallelism. In this paper, we present Garfield, a GPU-accelerated framework for multi-attribute range filtered ANNS that overcomes these bottlenecks through designing a lightweight index structure and hardware-aware execution pipeline. Garfield introduces the GMG index, which partitions data into cells and builds local graph indexes. It guarantees linear storage and indexing overhead by adding a constant number of cross-cell edges. For queries, Garfield utilizes a cluster-guided ordering strategy that reorders query-relevant cells, enabling a highly efficient cell-by-cell traversal on the GPU that aggressively reuses candidates as entry points across cells. To handle datasets exceeding GPU memory, Garfield features a cell-oriented out-of-core pipeline. It dynamically schedules cells to minimize the number of active queries per batch and overlaps GPU computation with CPU-to-GPU index streaming. Extensive evaluations demonstrate that Garfield reduces index size by 4.4x, while delivering 119.8x higher throughput than state-of-the-art RFANNS methods.