{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:56:51Z","timestamp":1769853411563,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607045","type":"proceedings-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T20:34:48Z","timestamp":1698698088000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Co-design Hardware and Algorithm for Vector Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3895-7943","authenticated-orcid":false,"given":"Wenqi","family":"Jiang","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0022-7865","authenticated-orcid":false,"given":"Shigang","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Bejing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3340-1060","authenticated-orcid":false,"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1500-7411","authenticated-orcid":false,"given":"Johannes","family":"De Fine Licht","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2825-6430","authenticated-orcid":false,"given":"Zhenhao","family":"He","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4901-5476","authenticated-orcid":false,"given":"Runbin","family":"Shi","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3271-3059","authenticated-orcid":false,"given":"Cedric","family":"Renggli","sequence":"additional","affiliation":[{"name":"Apple, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7866-4611","authenticated-orcid":false,"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-1854","authenticated-orcid":false,"given":"Theodoros","family":"Rekatsinas","sequence":"additional","affiliation":[{"name":"Apple, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4396-6695","authenticated-orcid":false,"given":"Gustavo","family":"Alonso","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n.d.]. https:\/\/www.intel.com\/content\/www\/us\/en\/software\/programmable\/sdk-for-opencl\/overview.html."},{"key":"e_1_3_2_2_2_1","unstructured":"[n.d.]. RocksDB in Microsoft Bing. https:\/\/blogs.bing.com\/Engineering-Blog\/october-2021\/RocksDB-in-Microsoft-Bing."},{"key":"e_1_3_2_2_3_1","unstructured":"[n.d.]. Vivado High-Level Synthesis. https:\/\/www.xilinx.com\/products\/design-tools\/vivado\/integration\/esl-design.html."},{"key":"e_1_3_2_2_4_1","unstructured":"[n.d.]. Worldwide visits to Google.com. https:\/\/www.statista.com\/statistics\/268252\/web-visitor-traffic-to-googlecom\/."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/215399.215427"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378126"},{"key":"e_1_3_2_2_7_1","volume-title":"The inverted multi-index","author":"Babenko Artem","year":"2014","unstructured":"Artem Babenko and Victor Lempitsky. 2014. The inverted multi-index. IEEE transactions on pattern analysis and machine intelligence 37, 6 (2014), 1247--1260."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-015-0069-3"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1468075.1468121"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609451"},{"key":"e_1_3_2_2_11_1","unstructured":"Sebastian Borgeaud Arthur Mensch Jordan Hoffmann Trevor Cai Eliza Rutherford Katie Millican George van den Driessche Jean-Baptiste Lespiau Bogdan Damoc Aidan Clark et al. 2021. Improving language models by retrieving from trillions of tokens. arXiv preprint arXiv:2112.04426 (2021)."},{"key":"e_1_3_2_2_12_1","volume-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2111.08566","author":"Chen Qi","year":"2021","unstructured":"Qi Chen, Bing Zhao, Haidong Wang, Mingqin Li, Chuanjie Liu, Zengzhong Li, Mao Yang, and Jingdong Wang. 2021. SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2111.08566 (2021)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.04.033"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325018"},{"key":"e_1_3_2_2_15_1","volume-title":"TPU-KNN: K Nearest Neighbor Search at Peak FLOP\/s. arXiv preprint arXiv:2206.14286","author":"Chern Felix","year":"2022","unstructured":"Felix Chern, Blake Hechtman, Andy Davis, Ruiqi Guo, David Majnemer, and Sanjiv Kumar. 2022. TPU-KNN: K Nearest Neighbor Search at Peak FLOP\/s. arXiv preprint arXiv:2206.14286 (2022)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/155332.155333"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3039409"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375296"},{"key":"e_1_3_2_2_21_1","volume-title":"Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143","author":"Fu Cong","year":"2017","unstructured":"Cong Fu, Chao Xiang, Changxu Wang, and Deng Cai. 2017. Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143 (2017)."},{"key":"e_1_3_2_2_22_1","volume-title":"Optimized product quantization","author":"Ge Tiezheng","year":"2013","unstructured":"Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization. IEEE transactions on pattern analysis and machine intelligence 36, 4 (2013), 744--755."},{"key":"e_1_3_2_2_23_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_2_24_1","volume-title":"Realm: Retrieval-augmented language model pre-training. arXiv preprint arXiv:2002.08909","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. Realm: Retrieval-augmented language model pre-training. arXiv preprint arXiv:2002.08909 (2020)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00040"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370593"},{"key":"e_1_3_2_2_28_1","volume-title":"Energy, memory, and runtime tradeoffs for implementing collective communication operations. Supercomputing frontiers and innovations 1, 2","author":"Hoefler Torsten","year":"2014","unstructured":"Torsten Hoefler and Dmitry Moor. 2014. Energy, memory, and runtime tradeoffs for implementing collective communication operations. Supercomputing frontiers and innovations 1, 2 (2014), 58--75."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2014.6927413"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457240"},{"key":"e_1_3_2_2_32_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_33_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","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--128."},{"key":"e_1_3_2_2_34_1","unstructured":"Wenqi Jiang Zhenhao He Shuai Zhang Thomas B Preu\u00dfer Kai Zeng Liang Feng Jiansong Zhang Tongxuan Liu Yong Li Jingren Zhou et al. 2020. MicroRec: Accelerating Deep Recommendation Systems to Microseconds by Hardware and Data Structure Solutions. arXiv preprint arXiv:2010.05894 (2020)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467139"},{"key":"e_1_3_2_2_36_1","volume-title":"Data Processing with FP-GAs on Modern Architectures. In Companion of the 2023 International Conference on Management of Data. 77--82","author":"Jiang Wenqi","year":"2023","unstructured":"Wenqi Jiang, Dario Korolija, and Gustavo Alonso. 2023. Data Processing with FP-GAs on Modern Architectures. In Companion of the 2023 International Conference on Management of Data. 77--82."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_2_38_1","volume-title":"Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas O\u011fuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_2_40_1","volume-title":"ANNA: Specialized Architecture for Approximate Nearest Neighbor Search. In 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 169--183","author":"Lee Yejin","year":"2022","unstructured":"Yejin Lee, Hyunji Choi, Sunhong Min, Hyunseung Lee, Sangwon Beak, Dawoon Jeong, Jae W Lee, and Tae Jun Ham. 2022. ANNA: Specialized Architecture for Approximate Nearest Neighbor Search. In 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA). IEEE, 169--183."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.130"},{"key":"e_1_3_2_2_43_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_3_2_2_45_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_2_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-011-0232-z"},{"key":"e_1_3_2_2_47_1","volume-title":"ScispaCy: fast and robust models for biomedical natural language processing. arXiv preprint arXiv:1902.07669","author":"Neumann Mark","year":"2019","unstructured":"Mark Neumann, Daniel King, Iz Beltagy, and Waleed Ammar. 2019. ScispaCy: fast and robust models for biomedical natural language processing. arXiv preprint arXiv:1902.07669 (2019)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2018.00022"},{"key":"e_1_3_2_2_49_1","volume-title":"An Adaptable High-Throughput FPGA Merge Sorter for Accelerating Database Analytics. In 2020 30th International Conference on Field-Programmable Logic and Applications (FPL). IEEE, 65--72","author":"Papaphilippou Philippos","year":"2020","unstructured":"Philippos Papaphilippou, Chris Brooks, and Wayne Luk. 2020. An Adaptable High-Throughput FPGA Merge Sorter for Accelerating Database Analytics. In 2020 30th International Conference on Field-Programmable Logic and Applications (FPL). IEEE, 65--72."},{"key":"e_1_3_2_2_50_1","first-page":"10672","article-title":"Hm-ann: Efficient billion-point nearest neighbor search on heterogeneous memory","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. Advances in Neural Information Processing Systems 33 (2020), 10672--10684.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_51_1","volume-title":"NASCENT: Near-Storage Acceleration of Database Sort on SmartSSD. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 262--272","author":"Salamat Sahand","year":"2021","unstructured":"Sahand Salamat, Armin Haj Aboutalebi, Behnam Khaleghi, Joo Hwan Lee, Yang Seok Ki, and Tajana Rosing. 2021. NASCENT: Near-Storage Acceleration of Database Sort on SmartSSD. In The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. 262--272."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587638"},{"key":"e_1_3_2_2_53_1","volume-title":"IEEE International Conference on","volume":"3","author":"Sivic Josef","year":"2003","unstructured":"Josef Sivic and Andrew Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In Computer Vision, IEEE International Conference on, Vol. 3. IEEE Computer Society, 1470--1470."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2016.34"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15286-3_16"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/2735461.2735462"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415541"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.223"},{"key":"e_1_3_2_2_59_1","volume-title":"The calculation of molecular structural similarity: principles and practice. Molecular informatics 33, 6--7","author":"Willett Peter","year":"2014","unstructured":"Peter Willett. 2014. The calculation of molecular structural similarity: principles and practice. Molecular informatics 33, 6--7 (2014), 403--413."},{"key":"e_1_3_2_2_60_1","volume-title":"Alex AT Bui, and Majid Sarrafzadeh","author":"Woodbridge Jonathan","year":"2016","unstructured":"Jonathan Woodbridge, Bobak Mortazavi, Alex AT Bui, and Majid Sarrafzadeh. 2016. Improving biomedical signal search results in big data case-based reasoning environments. Pervasive and mobile computing 28 (2016), 69--80."},{"key":"e_1_3_2_2_61_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00517"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882930"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00057"}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607045","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:22Z","timestamp":1750178182000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":63,"alternative-id":["10.1145\/3581784.3607045","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607045","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}