Accelerating Graph Indexing for ANNS on Modern CPUs
Summary: Graph-based ANNS indexing (e.g., HNSW) is CPU-bound by distance computations and random memory accesses; Flash is a compact coding strategy optimized for modern CPUs to boost SIMD and cache locality in graph indexing. It delivers 10.4x–22.9x faster index construction on 10M–1B vectors across eight datasets, with equal or improved search performance. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mengzhao Wang (Zhejiang University)
- 2. Haotian Wu (Zhejiang University)
- 3. Xiangyu Ke (Zhejiang University)
- 4. Yunjun Gao (Zhejiang University)
- 5. Yifan Zhu (Zhejiang University)
- 6. Wenchao Zhou (Alibaba)
BibTeX Citation
@inproceedings{wang_sigmod25,
title = {{Accelerating Graph Indexing for ANNS on Modern CPUs}},
author = {Wang, Mengzhao and Wu, Haotian and Ke, Xiangyu and Gao, Yunjun and Zhu, Yifan and Zhou, Wenchao},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725260},
url = {https://dl.acm.org/doi/10.1145/3725260},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 9 of 9 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 29 of 29 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next