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

Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems 2026 Open access

Read full text
Authors: Fei Fang, Yi Liu, Chen Qian
DOI: 10.1145/3801489.3806852
Cited by: 1
References: 3

Abstract

We present d-HNSW, an RDMA-based vector search engine for disaggregated memory that overcomes network bottlenecks and layout fragmentation through hardware-algorithm co-designed representative index caching, RDMA-friendly remote storage layout, query-aware loading, and pipelined execution.

Fields of Study & Subjects

Advanced Data Storage Technologies Network Packet Processing and Optimization Cloud Computing and Resource Management

Publication details

Journal / source
Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems
Publisher
ACM
Pages
229–231
Publication date
26 May 2026