AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search
2026-02-26 • Databases
DatabasesInformation Retrieval
AI summaryⓘ
The authors studied systems that find similar high-dimensional data points stored on disks, which usually focus on reducing slow disk access times. They discovered that when dealing with very high-dimensional data, these systems spend more time doing calculations than waiting for disk access. Based on this, the authors designed AlayaLaser, a new system that organizes data and uses modern CPU features to speed up computations. They also added smart techniques to improve performance further. Their experiments showed that AlayaLaser not only outperforms existing disk-based systems but can also compete with systems that keep all data in memory.
approximate nearest neighbor searchhigh-dimensional vectorson-disk indexgraph-based indexI/O bottleneckcompute-boundSIMD instructionsroofline modelvector similarity searchperformance optimization
Authors
Weijian Chen, Haotian Liu, Yangshen Deng, Long Xiang, Liang Huang, Gezi Li, Bo Tang
Abstract
On-disk graph-based approximate nearest neighbor search (ANNS) is essential for large-scale, high-dimensional vector retrieval, yet its performance is widely recognized to be limited by the prohibitive I/O costs. Interestingly, we observed that the performance of on-disk graph-based index systems is compute-bound, not I/O-bound, with the rising of the vector data dimensionality (e.g., hundreds or thousands). This insight uncovers a significant optimization opportunity: existing on-disk graph-based index systems universally target I/O reduction and largely overlook computational overhead, which leaves a substantial performance improvement space. In this work, we propose AlayaLaser, an efficient on-disk graph-based index system for large-scale high-dimensional vector similarity search. In particular, we first conduct performance analysis on existing on-disk graph-based index systems via the adapted roofline model, then we devise a novel on-disk data layout in AlayaLaser to effectively alleviate the compute-bound, which is revealed by the above roofline model analysis, by exploiting SIMD instructions on modern CPUs. We next design a suite of optimization techniques (e.g., degree-based node cache, cluster-based entry point selection, and early dispatch strategy) to further improve the performance of AlayaLaser. We last conduct extensive experimental studies on a wide range of large-scale high-dimensional vector datasets to verify the superiority of AlayaLaser. Specifically, AlayaLaser not only surpasses existing on-disk graph-based index systems but also matches or even exceeds the performance of in-memory index systems.