d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory
ACM SIGMETRICS Performance Evaluation Review · 20.07.2026 · 54 (1) · 229-231
DOI: 10.1145/3820171.3806852 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM SIGMETRICS Performance Evaluation Review, online erschienen am 27.07.2026. Verfasst von Fei Fang und 2 weiteren Autor:innen. Die Arbeit nennt 6 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NSF (National Science Foundation).
Abstract (Originalsprache)
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.
Förderung
- NSF (National Science Foundation)
Zitieren
APA
Fang, F., Liu, Y., & Qian, C. (2026). d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory. ACM SIGMETRICS Performance Evaluation Review, 54(1), 229-231. https://doi.org/10.1145/3820171.3806852
Vancouver
Fang F, Liu Y, Qian C. d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory. ACM SIGMETRICS Performance Evaluation Review. 2026;54(1):229-231. doi:10.1145/3820171.3806852
BibTeX
@article{Fang2026,
author = {Fang, Fei and Liu, Yi and Qian, Chen},
title = {d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory},
journal = {ACM SIGMETRICS Performance Evaluation Review},
year = {2026},
volume = {54},
number = {1},
pages = {229--231},
doi = {10.1145/3820171.3806852}
}
EUVIMED