Scalable Distributed Vector Search via Accuracy Preserving Index Construction

TL;DR

This paper introduces SPIRE, a scalable distributed vector index for billions of vectors that maintains accuracy and efficiency, outperforming existing systems in throughput and scalability.

Contribution

SPIRE's novel balanced partitioning and recursive multi-level construction enable scalable, accurate, and high-throughput approximate nearest neighbor search at billions of vectors.

Findings

Achieves up to 9.64X higher throughput than state-of-the-art systems.

Handles up to 8 billion vectors across 46 nodes.

Maintains stable accuracy with predictable search costs.

Abstract

Scaling Approximate Nearest Neighbor Search (ANNS) to billions of vectors requires distributed indexes that balance accuracy, latency, and throughput. Yet existing index designs struggle with this tradeoff. This paper presents SPIRE, a scalable vector index based on two design decisions. First, it identifies a balanced partition granularity that avoids read-cost explosion. Second, it introduces an accuracy-preserving recursive construction that builds a multi-level index with predictable search cost and stable accuracy. In experiments with up to 8 billion vectors across 46 nodes, SPIRE achieves high scalability and up to 9.64X higher throughput than state-of-the-art systems.