{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:03:46Z","timestamp":1783577026817,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759777","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"789-804","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7734-7754","authenticated-orcid":false,"given":"Sitian","family":"Chen","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9773-9332","authenticated-orcid":false,"given":"Amelie Chi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8998-2411","authenticated-orcid":false,"given":"Yucheng","family":"Shi","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6623-350X","authenticated-orcid":false,"given":"Yusen","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5780-7900","authenticated-orcid":false,"given":"Xin","family":"Yao","sequence":"additional","affiliation":[{"name":"Huawei, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2021. SPACEV1B: A billion-Scale vector dataset for text descriptors. https:\/\/github.com\/microsoft\/SPTAG\/tree\/main\/datasets\/SPACEV1B."},{"key":"e_1_3_3_2_3_2","unstructured":"2023. Introducing the most advanced Processing In Memory product. https:\/\/www.upmem.com\/."},{"key":"e_1_3_3_2_4_2","unstructured":"2023. UPMEM User Manual. https:\/\/sdk.upmem.com\/2023.1.0\/index.html."},{"key":"e_1_3_3_2_5_2","unstructured":"2024. NVIDIA Nsight Systems. https:\/\/developer.nvidia.com\/nsight-systems."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT47387.2019.00019"},{"key":"e_1_3_3_2_7_2","unstructured":"Alexandr Andoni Piotr Indyk Thijs Laarhoven Ilya Razenshteyn and Ludwig Schmidt. 2015. Practical and optimal LSH for angular distance. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_3_2_8_2","first-page":"12","volume-title":"42nd International Conference on Very Large Data Bases","volume":"9","author":"Andr\u00e9 Fabien","year":"2016","unstructured":"Fabien Andr\u00e9, Anne-Marie Kermarrec, and Nicolas Le\u00a0Scouarnec. 2016. Cache locality is not enough: High-performance nearest neighbor search with product quantization fast scan. In 42nd International Conference on Very Large Data Bases , Vol.\u00a09. 12."},{"key":"e_1_3_3_2_9_2","unstructured":"Akhil Arora Sakshi Sinha Piyush Kumar and Arnab Bhattacharya. 2018. Hd-index: Pushing the scalability-accuracy boundary for approximate knn search in high-dimensional spaces. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1804.06829 (2018)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00080"},{"key":"e_1_3_3_2_11_2","first-page":"2055","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Babenko Artem","year":"2016","unstructured":"Artem Babenko and Victor Lempitsky. 2016. Efficient indexing of billion-scale datasets of deep descriptors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2055\u20132063."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592980.3595312"},{"key":"e_1_3_3_2_13_2","unstructured":"BytePlus. 2025. Advanced Feature: Vector Retrieval. https:\/\/docs.byteplus.com\/zh-CN\/docs\/bytehouse\/vector-retrieval."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Shuangyu Cai Boyu Tian Huanchen Zhang and Mingyu Gao. 2024. PimPam: Efficient Graph Pattern Matching on Real Processing-in-Memory Hardware. Proceedings of the ACM on Management of Data 2 3 (2024) 1\u201325.","DOI":"10.1145\/3654964"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070940"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557098"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Sitian Chen Haobin Tan Amelie\u00a0Chi Zhou Yusen Li and Pavan Balaji. 2024. UpDLRM: Accelerating Personalized Recommendation using Real-World PIM Architecture. Proceedings of the 56th Annual Design Automation Conference (DAC) (2024).","DOI":"10.1145\/3649329.3658266"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_2_19_2","unstructured":"Facebook AI Research. [n. d.]. Faiss. https:\/\/github.com\/facebookresearch\/faiss."},{"key":"e_1_3_3_2_20_2","first-page":"155","volume-title":"European Conference on Parallel Processing","author":"Falevoz Yann","year":"2023","unstructured":"Yann Falevoz and Julien Legriel. 2023. Energy efficiency impact of processing in memory: A comprehensive review of workloads on the upmem architecture. In European Conference on Parallel Processing. Springer, 155\u2013166."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Jianyang Gao and Cheng Long. 2023. High-dimensional approximate nearest neighbor search: with reliable and efficient distance comparison operations. Proceedings of the ACM on Management of Data 1 2 (2023) 1\u201327.","DOI":"10.1145\/3589282"},{"key":"e_1_3_3_2_22_2","unstructured":"Christina Giannoula Peiming Yang Ivan\u00a0Fernandez Vega Jiacheng Yang Yu\u00a0Xin Li Juan\u00a0Gomez Luna Mohammad Sadrosadati Onur Mutlu and Gennady Pekhimenko. 2024. Accelerating Graph Neural Networks on Real Processing-In-Memory Systems. arxiv:https:\/\/arXiv.org\/abs\/2402.16731\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2402.16731"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Kailash Gogineni Sai\u00a0Santosh Dayapule Juan G\u00f3mez-Luna Karthikeya Gogineni Peng Wei Tian Lan Mohammad Sadrosadati Onur Mutlu and Guru Venkataramani. 2024. SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.03967 (2024).","DOI":"10.1109\/ISPASS61541.2024.00029"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Long Gong Huayi Wang Mitsunori Ogihara and Jun Xu. 2020. iDEC: indexable distance estimating codes for approximate nearest neighbor search. Proceedings of the VLDB Endowment 13 9 (2020).","DOI":"10.14778\/3397230.3397243"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Fabian Groh Lukas Ruppert Patrick Wieschollek and Hendrik\u00a0PA Lensch. 2022. Ggnn: Graph-based gpu nearest neighbor search. IEEE Transactions on Big Data 9 1 (2022) 267\u2013279.","DOI":"10.1109\/TBDATA.2022.3161156"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Juan G\u00f3mez-Luna Izzat\u00a0El Hajj Ivan Fernandez Christina Giannoula Geraldo\u00a0F. Oliveira and Onur Mutlu. 2022. Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System. IEEE Access 10 (2022) 52565\u201352608.","DOI":"10.1109\/ACCESS.2022.3174101"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"e_1_3_3_2_28_2","unstructured":"Intel. 2017. Intel Xeon Silver 4110 Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/123547\/intel-xeon-silver-4110-processor-11m-cache-2-10-ghz\/specifications.html."},{"key":"e_1_3_3_2_29_2","first-page":"585","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). Boston, MA, 585\u2013600."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Herve Jegou Matthijs Douze and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence 33 1 (2010) 117\u2013128.","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946540"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607045"},{"key":"e_1_3_3_2_33_2","unstructured":"Wenqi Jiang Marco Zeller Roger Waleffe Torsten Hoefler and Gustavo Alonso. 2023. Chameleon: a heterogeneous and disaggregated accelerator system for retrieval-augmented language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.09949 (2023)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00300"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Jeff Johnson Matthijs Douze and Herv\u00e9 J\u00e9gou. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data 7 3 (2019) 535\u2013547.","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_3_2_36_2","unstructured":"Saim Khan Somesh Singh Harsha\u00a0Vardhan Simhadri Jyothi Vedurada et\u00a0al. 2024. BANG: Billion-Scale Approximate Nearest Neighbor Search using a Single GPU. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.11324 (2024)."},{"key":"e_1_3_3_2_37_2","unstructured":"Urvashi Khandelwal Omer Levy Dan Jurafsky Luke Zettlemoyer and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1911.00172 (2019)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Ji-Hoon Kim Yeo-Reum Park Jaeyoung Do Soo-Young Ji and Joo-Young Kim. 2023. Accelerating Large-Scale Graph-Based Nearest Neighbor Search on a Computational Storage Platform. IEEE Trans. Comput. 72 1 (2023) 278\u2013290.","DOI":"10.1109\/TC.2022.3155956"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00093"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00021"},{"key":"e_1_3_3_2_41_2","first-page":"3099","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"LeJeune Daniel","year":"2019","unstructured":"Daniel LeJeune, Reinhard Heckel, and Richard Baraniuk. 2019. Adaptive estimation for approximate k -nearest-neighbor computations. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 3099\u20133107."},{"key":"e_1_3_3_2_42_2","unstructured":"Shiyu Li Yitu Wang Edward Hanson Andrew Chang Yang\u00a0Seok Ki Hai\u00a0Helen Li and Yiran Chen. 2024. NDRec: A Near-Data Processing System for Training Large-Scale Recommendation Models. IEEE Trans. Comput. (2024)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546723"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640360"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Yu\u00a0A Malkov and Dmitry\u00a0A 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\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638475"},{"key":"e_1_3_3_2_47_2","unstructured":"Nvidia. 2020. NVIDIA A100. https:\/\/www.nvidia.cn\/data-center\/a100\/."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676947"},{"key":"e_1_3_3_2_49_2","unstructured":"Weijia Shi Sewon Min Maria Lomeli Chunting Zhou Margaret Li Gergely Szilvasy Rich James Xi\u00a0Victoria Lin Noah\u00a0A Smith Luke Zettlemoyer et\u00a0al. 2023. In-context pretraining: Language modeling beyond document boundaries. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.10638 (2023)."},{"key":"e_1_3_3_2_50_2","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Tian Bing","year":"2024","unstructured":"Bing Tian, Haikun Liu, Zhuohui Duan, Xiaofei Liao, Hai Jin, and Yu Zhang. 2024. Scalable Billion-point Approximate Nearest Neighbor Search Using SmartSSDs. In 2024 USENIX Annual Technical Conference (USENIX ATC 24)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Yitu Wang Shiyu Li Qilin Zheng Andrew Chang Hai Li and Yiran Chen. 2023. EMS-i: An Efficient Memory System Design with Specialized Caching Mechanism for Recommendation Inference. ACM Transactions on Embedded Computing Systems 22 5s (2023) 1\u201322.","DOI":"10.1145\/3609384"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00035"},{"key":"e_1_3_3_2_53_2","unstructured":"Weihong Xu Junwei Chen Po-Kai Hsu Jaeyoung Kang Minxuan Zhou Sumukh Pinge Shimeng Yu and Tajana Rosing. 2023. Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.04257 (2023)."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00332"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"Wei Yuan and Xi Jin. 2025. FANNS: An FPGA-Based Approximate Nearest-Neighbor Search Accelerator. IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2025).","DOI":"10.1109\/TVLSI.2024.3496589"},{"key":"e_1_3_3_2_56_2","series-title":"Proceedings of Machine Learning Research","first-page":"58484","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Zhai Jiaqi","year":"2024","unstructured":"Jiaqi Zhai, Lucy Liao, Xing Liu, Yueming Wang, Rui Li, Xuan Cao, Leon Gao, Zhaojie Gong, Fangda Gu, Jiayuan He, Yinghai Lu, and Yu Shi. 2024. Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations. In Proceedings of the 41st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 58484\u201358509."},{"key":"e_1_3_3_2_57_2","unstructured":"Hailin Zhang Xiaodong Ji Yilin Chen Fangcheng Fu Xupeng Miao Xiaonan Nie Weipeng Chen and Bin Cui. 2025. PQCache: Product Quantization-based KVCache for Long Context LLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2407.12820\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.12820"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00094"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"crossref","unstructured":"Bolong Zheng Zhao Xi Lianggui Weng Nguyen Quoc\u00a0Viet Hung Hang Liu and Christian\u00a0S Jensen. 2020. PM-LSH: A fast and accurate LSH framework for high-dimensional approximate NN search. Proceedings of the VLDB Endowment 13 5 (2020) 643\u2013655.","DOI":"10.14778\/3377369.3377374"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882930"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:43:18Z","timestamp":1773254598000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759777"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":59,"alternative-id":["10.1145\/3712285.3759777","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759777","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}