{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:54:33Z","timestamp":1775638473338,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2322919, 2420632, 2426031, 2426940"],"award-info":[{"award-number":["2322919, 2420632, 2426031, 2426940"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,10]]},"DOI":"10.1145\/3736548.3737822","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T09:10:22Z","timestamp":1750669822000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Vector Search on Disaggregated Memory with d-HNSW"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8839-9508","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"University of California Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3709-6749","authenticated-orcid":false,"given":"Fei","family":"Fang","sequence":"additional","affiliation":[{"name":"University of California Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6882-9590","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[{"name":"University of California Santa Cruz, Santa Cruz, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604833"},{"key":"e_1_3_2_1_2_1","unstructured":"DeepSeek. [n.d.]. https:\/\/www.deepseek.com\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006219"},{"key":"e_1_3_2_1_4_1","unstructured":"Fire flyer file system. [n.d.]. https:\/\/github.com\/deepseek-ai\/3FS\/."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_2_1_6_1","first-page":"518","article-title":"Similarity search in high dimensions via hashing","volume":"99","author":"Gionis Aristides","year":"1999","unstructured":"Aristides Gionis, Piotr Indyk, Rajeev Motwani, et al. 1999. Similarity search in high dimensions via hashing. In Vldb, Vol. 99. 518--529.","journal-title":"Vldb"},{"key":"e_1_3_2_1_7_1","volume-title":"Memserve: Context caching for disaggregated llm serving with elastic memory pool. arXiv preprint arXiv:2406.17565","author":"Hu Cunchen","year":"2024","unstructured":"Cunchen Hu, Heyang Huang, Junhao Hu, Jiang Xu, Xusheng Chen, Tao Xie, Chenxi Wang, Sa Wang, Yungang Bao, Ninghui Sun, et al. 2024. Memserve: Context caching for disaggregated llm serving with elastic memory pool. arXiv preprint arXiv:2406.17565 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Jang Junhyeok","year":"2023","unstructured":"Junhyeok Jang, Hanjin Choi, Hanyeoreum Bae, Seungjun Lee, Miryeong Kwon, and Myoungsoo Jung. 2023. CXL-ANNS:Software-Hardware collaborative memory disaggregation and computation for Billion-Scale approximate nearest neighbor search. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 585--600."},{"key":"e_1_3_2_1_9_1","volume-title":"Ragcache: Efficient knowledge caching for retrieval-augmented generation. arXiv preprint arXiv:2404.12457","author":"Jin Chao","year":"2024","unstructured":"Chao Jin, Zili Zhang, Xuanlin Jiang, Fangyue Liu, Xin Liu, Xuanzhe Liu, and Xin Jin. 2024. Ragcache: Efficient knowledge caching for retrieval-augmented generation. arXiv preprint arXiv:2404.12457 (2024)."},{"key":"e_1_3_2_1_10_1","unstructured":"Anuj Kalia Michael Kaminsky and David G Andersen. 2016. Design guidelines for high performance RDMA systems. In 2016 USENIX annual technical conference (USENIX ATC 16). 437--450."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380600"},{"key":"e_1_3_2_1_12_1","volume-title":"ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory Systems. In 21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Li Pengfei","year":"2023","unstructured":"Pengfei Li, Yu Hua, Pengfei Zuo, Zhangyu Chen, and Jiajie Sheng. 2023. ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory Systems. In 21st USENIX Conference on File and Storage Technologies (FAST 23). 99--114."},{"key":"e_1_3_2_1_13_1","unstructured":"A library for efficient similarity search and clustering of dense vectors. [n.d.]. https:\/\/github.com\/facebookresearch\/faiss."},{"key":"e_1_3_2_1_14_1","volume-title":"Retrievalattention: Accelerating long-context llm inference via vector retrieval. arXiv preprint arXiv:2409.10516","author":"Liu Di","year":"2024","unstructured":"Di Liu, Meng Chen, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, et al. 2024. Retrievalattention: Accelerating long-context llm inference via vector retrieval. arXiv preprint arXiv:2409.10516 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3705829.3705849"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3675034.3675050"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695959"},{"key":"e_1_3_2_1_18_1","volume-title":"SMART: A High-Performance Adaptive Radix Tree for Disaggregated Memory. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Luo Xuchuan","year":"2023","unstructured":"Xuchuan Luo, Pengfei Zuo, Jiacheng Shen, Jiazhen Gu, Xin Wang, Michael R Lyu, and Yangfan Zhou. 2023. SMART: A High-Performance Adaptive Radix Tree for Disaggregated Memory. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 553--571."},{"key":"e_1_3_2_1_19_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42, 4 (2018), 824--836."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230557"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-024-00864-x"},{"key":"e_1_3_2_1_22_1","volume-title":"Mooncake: A kvcache-centric disaggregated architecture for llm serving. arXiv preprint arXiv:2407.00079","author":"Qin Ruoyu","year":"2024","unstructured":"Ruoyu Qin, Zheming Li, Weiran He, Mingxing Zhang, Yongwei Wu, Weimin Zheng, and Xinran Xu. 2024. Mooncake: A kvcache-centric disaggregated architecture for llm serving. arXiv preprint arXiv:2407.00079 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330875"},{"key":"e_1_3_2_1_24_1","volume-title":"Lin (Eds.)","volume":"33","author":"Ren Jie","year":"2020","unstructured":"Jie Ren, Minjia Zhang, and Dong Li. 2020. HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 10672--10684. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/788d986905533aba051261497ecffcbb-Paper.pdf"},{"key":"e_1_3_2_1_25_1","unstructured":"CloudLab: Flexible scientific infrastructure for research on the future of cloud computing. [n.d.]. https:\/\/www.cloudlab.us."},{"key":"e_1_3_2_1_26_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Shan Yizhou","year":"2018","unstructured":"Yizhou Shan, Yutong Huang, Yilun Chen, and Yiying Zhang. 2018. LegoOS: A disseminated, distributed OS for hardware resource disaggregation. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 69--87."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613144"},{"key":"e_1_3_2_1_28_1","volume-title":"21st USENIX Conference on File and Storage Technologies (FAST 23)","author":"Shen Jiacheng","year":"2023","unstructured":"Jiacheng Shen, Pengfei Zuo, Xuchuan Luo, Tianyi Yang, Yuxin Su, Yangfan Zhou, and Michael R Lyu. 2023. FUSEE: A fully Memory-DisaggregatedKey-Value store. In 21st USENIX Conference on File and Storage Technologies (FAST 23). 81--98."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657683"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654990"},{"key":"e_1_3_2_1_31_1","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Tsai Shin-Yeh","year":"2020","unstructured":"Shin-Yeh Tsai, Yizhou Shan, and Yiying Zhang. 2020. Disaggregating persistent memory and controlling them remotely: An exploration of passive disaggregated Key-Value stores. In 2020 USENIX Annual Technical Conference (USENIX ATC 20). 33--48."},{"key":"e_1_3_2_1_32_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Wang Chenxi","year":"2020","unstructured":"Chenxi Wang, Haoran Ma, Shi Liu, Yuanqi Li, Zhenyuan Ruan, Khanh Nguyen, Michael D Bond, Ravi Netravali, Miryung Kim, and Guoqing Harry Xu. 2020. Semeru: A Memory-Disaggregated managed runtime. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 261--280."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685911"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589403"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517824"},{"key":"e_1_3_2_1_37_1","volume-title":"The case for distributed shared-memory databases with rdma-enabled memory disaggregation. arXiv preprint arXiv:2207.03027","author":"Wang Ruihong","year":"2022","unstructured":"Ruihong Wang, Jianguo Wang, Stratos Idreos, M Tamer \u00d6zsu, and Walid G Aref. 2022. The case for distributed shared-memory databases with rdma-enabled memory disaggregation. arXiv preprint arXiv:2207.03027 (2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00217"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690825"},{"key":"e_1_3_2_1_40_1","volume-title":"Characterizing Off-path SmartNIC for Accelerating Distributed Systems. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Wei Xingda","year":"2023","unstructured":"Xingda Wei, Rongxin Cheng, Yuhan Yang, Rong Chen, and Haibo Chen. 2023. Characterizing Off-path SmartNIC for Accelerating Distributed Systems. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 987--1004."},{"key":"e_1_3_2_1_41_1","volume-title":"LightTraffic: On Optimizing CPU-GPU Data Traffic for Efficient Large-scale Random Walks. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 882--895","author":"Xing Yipeng","year":"2023","unstructured":"Yipeng Xing, Yongkun Li, Zhiqiang Wang, Yinlong Xu, and John CS Lui. 2023. LightTraffic: On Optimizing CPU-GPU Data Traffic for Efficient Large-scale Random Walks. In 2023 IEEE 39th International Conference on Data Engineering (ICDE). IEEE, 882--895."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357938"},{"key":"e_1_3_2_1_43_1","volume-title":"Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhang Ming","year":"2024","unstructured":"Ming Zhang, Yu Hua, and Zhijun Yang. 2024. Motor: Enabling Multi-Versioning for Distributed Transactions on Disaggregated Memory. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 801--819."},{"key":"e_1_3_2_1_44_1","volume-title":"20th USENIX Conference on File and Storage Technologies (FAST 22)","author":"Zhang Ming","year":"2022","unstructured":"Ming Zhang, Yu Hua, Pengfei Zuo, and Lurong Liu. 2022. FORD: Fast one-sided RDMA-based distributed transactions for disaggregated persistent memory. In 20th USENIX Conference on File and Storage Technologies (FAST 22). 51--68."},{"key":"e_1_3_2_1_45_1","volume-title":"Approximate Vector Queries on Very Large Unstructured Datasets. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang Zili","year":"2023","unstructured":"Zili Zhang, Chao Jin, Linpeng Tang, Xuanzhe Liu, and Xin Jin. 2023. Fast, Approximate Vector Queries on Very Large Unstructured Datasets. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 995--1011."},{"key":"e_1_3_2_1_46_1","volume-title":"Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Zhang Zili","year":"2024","unstructured":"Zili Zhang, Fangyue Liu, Gang Huang, Xuanzhe Liu, and Xin Jin. 2024. Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 23--40."},{"key":"e_1_3_2_1_47_1","volume-title":"HiDPU: A DPU-Oriented Hybrid Indexing Scheme for Disaggregated Storage Systems. In 23rd USENIX Conference on File and Storage Technologies (FAST 25)","author":"Zhu Wenbin","year":"2025","unstructured":"Wenbin Zhu, Zhaoyan Shen, Qian Wei, Renhai Chen, Xin Yao, Dongxiao Yu, and Zili Shao. 2025. HiDPU: A DPU-Oriented Hybrid Indexing Scheme for Disaggregated Storage Systems. In 23rd USENIX Conference on File and Storage Technologies (FAST 25). 271--285."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511895"}],"event":{"name":"HotStorage '25: 17th ACM Workshop on Hot Topics in Storage and File Systems","location":"Boston MA USA","acronym":"HotStorage '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 17th ACM Workshop on Hot Topics in Storage and File Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3736548.3737822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:03:09Z","timestamp":1755914589000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3736548.3737822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":48,"alternative-id":["10.1145\/3736548.3737822","10.1145\/3736548"],"URL":"https:\/\/doi.org\/10.1145\/3736548.3737822","relation":{},"subject":[],"published":{"date-parts":[[2025,7,10]]},"assertion":[{"value":"2025-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}