arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.13591cs.DB
收藏

d-HNSW:一种基于解耦内存的高性能向量搜索引擎

d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory

University of California, Santa Cruz(加州大学圣克鲁兹分校)

Fei Fang, Yi Liu, Chen Qian

AI总结:

d-HNSW是首个针对解耦内存系统的RDMA-based向量搜索引擎,通过硬件算法协同设计解决指针追逐、非连续内存布局、冗余数据传输和资源利用率低等问题,实现高准确度和高吞吐量。

摘要:

高效的向量搜索对于驱动大规模AI应用,如大语言模型至关重要。现有解决方案针对单体架构设计,其中计算和内存紧密耦合。最近,解耦架构打破了这种耦合,通过将计算和内存资源分离为独立可扩展的池来提高利用率。然而,将向量数据库应用于解耦内存系统给系统设计带来了独特的挑战,因为其基于图的索引。我们提出了d-HNSW,这是首个针对解耦内存系统的RDMA-based向量搜索引擎。d-HNSW在保持HNSW的高精度的同时,解决了解耦引入的新系统级挑战:1)指针追逐遍历导致的网络效率低下,2)动态插入引起的非连续远程内存布局,3)批量工作负载中的冗余数据传输,4)由于顺序执行导致的资源利用率低下。d-HNSW通过一系列硬件算法协同设计技术来解决这些问题,包括1)平衡聚类与轻量级代表索引以减少网络往返和确保可预测的延迟,2)一种RDMA友好的图布局,在动态插入下保持数据连续性,3)查询感知的数据加载以消除跨批量查询的冗余获取,4)流水线执行模型,将RDMA传输与计算重叠以隐藏网络延迟并提高吞吐量。在公共云上的评估结果表明,d-HNSW相比其他基线,查询延迟降低至10^-2倍,查询吞吐量提高100倍,同时保持94%的高召回率。

英文摘要:

Efficient vector search is essential for powering large-scale AI applications, such as LLMs. Existing solutions are designed for monolithic architectures where compute and memory are tightly coupled. Recently, disaggregated architecture breaks this coupling by separating compution and memory resources into independently scalable pools to improve utilization. However, applying vector database on disaggregated memory system brings unique challenges to system design due to its graph-based index. We present d-HNSW, the first RDMA-based vector search engine optimized for disaggregated memory systems. d-HNSW preserves HNSW's high accuracy while addressing the new system-level challenges introduced by disaggregation: 1) network inefficiency from pointer-chasing traversals, 2) non-contiguous remote memory layout induced by dynamic insertions, 3) redundant data transfers in batch workloads, and 4) resource underutilization due to sequential execution. d-HNSW tackles these challenges through a set of hardware-algorithm co-designed techniques, including 1) balanced clustering with a lightweight representative index to reduce network round-trips and ensure predictable latency, 2) an RDMA-friendly graph layout that preserves data contiguity under dynamic insertions, 3) query-aware data loading to eliminate redundant fetches across batch queries, and 4) a pipelined execution model that overlaps RDMA transfers with computation to hide network latency and improve throughput. Our evaluation results in a public cloud show that d-HNSW achieves up to < 10-2x query latency and > 100x query throughput compared to other baselines, while maintaining a high recall of 94%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑