# Breaking the Storage-Compute Bottleneck in Billion-Scale ANNS: A GPU-Driven Asynchronous I/O Framework

arXiv: https://arxiv.org/abs/2507.10070 · HTML: https://mlsanity.com/paper/2507.10070/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2025.

## Built on by (most cited first, 2 of 2)

- [GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions](https://mlsanity.com/paper/2602.16719/) (2026)
- [The Hybrid Multimodal Graph Index (HMGI): A Comprehensive Framework for Integrated Relational and Vector Search](https://mlsanity.com/paper/2510.10123/) (2025)

## Abstract (arXiv)

With the advancement of information retrieval, recommendation systems, and Retrieval-Augmented Generation (RAG), Approximate Nearest Neighbor Search (ANNS) gains widespread applications due to its higher performance and accuracy. While several disk-based ANNS systems have emerged to handle exponentially growing vector datasets, they suffer from suboptimal performance due to two inherent limitations: 1) failing to overlap SSD accesses with distance computation processes and 2) extended I/O latency caused by suboptimal I/O Stack. To address these challenges, we present FlashANNS, a GPU-accelerated out-of-core graph-based ANNS system through I/O-compute overlapping. Our core insight lies in the synchronized orchestration of I/O and computation through three key innovations: 1) Dependency-Relaxed asynchronous pipeline: FlashANNS decouples I/O-computation dependencies to fully overlap between GPU distance calculations and SSD data transfers. 2) Warp-Level concurrent SSD access: FlashANNS implements a lock-free I/O stack with warp-level concurrency control, to reduce the latency-induced time overhead. 3) Computation-I/O balanced graph degree Selection: FlashANNS selects graph degrees via lightweight compute-to-I/O ratio sampling, ensuring optimal balance between computational load and storage access latency across different I/O bandwidth configurations. We implement FlashANNS and compare it with state-of-the-art out-of-core ANNS systems (SPANN, DiskANN) and a GPU-accelerated out-of-core ANNS system (FusionANNS). Experimental results demonstrate that at ≥95% recall@10 accuracy, our method achieves 2.3-5.9× higher throughput compared to existing SOTA methods with a single SSD, and further attains 2.7-12.2× throughput improvement in multi-SSD configurations.