SHARD: A Scalable and Resize-optimized Hash Index on Disaggregated Memory
Summary: SHARD targets one-RTT hash indexing over disaggregated memory with Iceberg Hashing and Ordered-CAS, reducing RDMA accesses while preserving duplicate-key correctness. Lazy resizing, RDMA combining, and adaptive synchronization cut resize and coordination costs, delivering up to 6.7× gains. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hantian Zha (Renmin University of China)
- 2. Teng Ma (Alibaba)
- 3. Baotong Lu (Microsoft)
- 4. Yuansen Wang (Renmin University of China)
- 5. Dongbiao He (Computer Network Information Center, Chinese Academy of Sciences)
- 6. Yuanhui Luo (Renmin University of China)
- 7. Dafang Zhang (Renmin University of China)
- 8. Yunpeng Chai (Renmin University of China)
- 9. Yuxing Chen (Tencent)
- 10. Anqun Pan (Tencent)
BibTeX Citation
@article{zha_vldb26,
title = {{SHARD: A Scalable and Resize-optimized Hash Index on Disaggregated Memory}},
author = {Zha, Hantian and Ma, Teng and Lu, Baotong and Wang, Yuansen and He, Dongbiao and Luo, Yuanhui and Zhang, Dafang and Chai, Yunpeng and Chen, Yuxing and Pan, Anqun},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {4},
pages = {684--697},
doi = {10.14778/3785297.3785309},
url = {https://doi.org/10.14778/3785297.3785309},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 16 of 16 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next