{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T04:12:06Z","timestamp":1793247126737,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":344,"publisher":"ACM","funder":[{"name":"ETH Future Computing Laboratory (EFCL)"},{"name":"Huawei ZRC Storage Team"},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Chip Center for Emerging Smart Systems (ACCESS), sponsored by InnoHK funding, Hong Kong SAR"},{"name":"European Union\u2019s Horizon programme for research and innovation","award":["101047160 - BioPIM"],"award-info":[{"award-number":["101047160 - BioPIM"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00347394, RS-2024-00415602, RS-2024-00459026"],"award-info":[{"award-number":["RS-2024-00347394, RS-2024-00415602, RS-2024-00459026"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731116","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T12:43:11Z","timestamp":1750423391000},"page":"1171-1192","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8624-4497","authenticated-orcid":false,"given":"Kangqi","family":"Chen","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4709-2323","authenticated-orcid":false,"given":"Rakesh","family":"Nadig","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2536-7082","authenticated-orcid":false,"given":"Manos","family":"Frouzakis","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0833-0042","authenticated-orcid":false,"given":"Nika Mansouri","family":"Ghiasi","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7754-9427","authenticated-orcid":false,"given":"Yu","family":"Liang","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7393-4504","authenticated-orcid":false,"given":"Haiyu","family":"Mao","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland and King's College London (KCL), London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1826-9003","authenticated-orcid":false,"given":"Jisung","family":"Park","sequence":"additional","affiliation":[{"name":"POSTECH, Pohang, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-0175","authenticated-orcid":false,"given":"Mohammad","family":"Sadrosadati","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0075-2312","authenticated-orcid":false,"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2004. FastBit: An Efficient Compressed Bitmap Index Technology. https:\/\/sdm.lbl.gov\/fastbit\/."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Anurag Acharya Mustafa Uysal and Joel Saltz. 1998. Active Disks: Programming Model Algorithms and Evaluation. ASPLOS (1998).","DOI":"10.1145\/291069.291026"},{"key":"e_1_3_3_1_4_2","volume-title":"USENIX ATC","author":"Agrawal Nitin","year":"2008","unstructured":"Nitin Agrawal, Vijayan Prabhakaran, Ted Wobber, John\u00a0D Davis, Mark Manasse, and Rina Panigrahy. 2008. Design Tradeoffs for SSD Performance. In USENIX ATC."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3533737.3535090"},{"key":"e_1_3_3_1_6_2","unstructured":"Voyage AI. 2024. voyage-multilingual-2: Multilingual Embedding Model. https:\/\/blog.voyageai.com\/2024\/06\/10\/voyage-multilingual-2-multilingual-embedding-model\/"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Joshua Ainslie James Lee-Thorp Michiel de Jong Yury Zemlyanskiy Federico Lebr\u00f3n and Sumit Sanghai. 2023. Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13245 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00025"},{"key":"e_1_3_3_1_9_2","unstructured":"Amazon Web Services. 2024. Build a RAG data ingestion pipeline for large-scale ML workloads. https:\/\/aws.amazon.com\/blogs\/big-data\/build-a-rag-data-ingestion-pipeline-for-large-scale-ml-workloads\/."},{"key":"e_1_3_3_1_10_2","unstructured":"AMD. 2023. EPYC\u2122 9554. https:\/\/www.amd.com\/en\/products\/processors\/server\/epyc\/4th-generation-9004-and-8004-series\/amd-epyc-9554.html"},{"key":"e_1_3_3_1_11_2","unstructured":"AMD. 2024. AMD\u00ae \u03bc Prof. https:\/\/www.amd.com\/en\/developer\/uprof.html"},{"key":"e_1_3_3_1_12_2","volume-title":"Datasets for approximate nearest neighbor search","author":"Amsaleg Laurent","year":"2010","unstructured":"Laurent Amsaleg and Herv\u00e9 J\u00e9gou. 2010. Datasets for approximate nearest neighbor search. http:\/\/corpus-texmex.irisa. fr\/"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806534"},{"key":"e_1_3_3_1_14_2","unstructured":"Arm. 2016. Cortex-R8. https:\/\/www.arm.com\/products\/silicon-ip-cpu\/cortex-r\/cortex-r8"},{"key":"e_1_3_3_1_15_2","unstructured":"Arm. 2020. Arm Storage Solution for SSD Controllers. https:\/\/armkeil.blob.core.windows.net\/developer\/Files\/pdf\/solution-brief\/arm-storage-solution-for-ssd-solutions-brief.pdf"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Sunil Arya David\u00a0M Mount Nathan\u00a0S Netanyahu Ruth Silverman and Angela\u00a0Y Wu. 1998. An optimal algorithm for approximate nearest neighbor searching fixed dimensions. Journal of the ACM (JACM) 45 6 (1998) 891\u2013923.","DOI":"10.1145\/293347.293348"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02209"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2507847"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Rajeev Balasubramonian Andrew\u00a0B Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New tools for interconnect exploration in innovative off-chip memories. ACM Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.50"},{"key":"e_1_3_3_1_21_2","unstructured":"Parishad BehnamGhader Vaibhav Adlakha Marius Mosbach Dzmitry Bahdanau Nicolas Chapados and Siva Reddy. 2024. Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.05961 (2024)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480133"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232366"},{"key":"e_1_3_3_1_24_2","unstructured":"Sebastian Bruch Aditya Krishnan and Franco\u00a0Maria Nardini. 2024. Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.12207 (2024)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Yu Cai Saugata Ghose Erich\u00a0F. Haratsch Yixin Luo and Onur Mutlu. 2017. Error Characterization Mitigation and Recovery in Flash-Memory-Based Solid-State Drives. Proc. IEEE (2017).","DOI":"10.1109\/JPROC.2017.2713127"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Yu Cai Saugata Ghose Erich\u00a0F Haratsch Yixin Luo and Onur Mutlu. 2017. Error Characterization Mitigation and Recovery in Flash-Memory-Based Solid-State Drives. Proc. IEEE (2017).","DOI":"10.1109\/JPROC.2017.2713127"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0599-3_9"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-0599-3_9"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.61"},{"key":"e_1_3_3_1_31_2","volume-title":"DATE","author":"Cai Yu","year":"2012","unstructured":"Yu Cai, Erich\u00a0F Haratsch, Onur Mutlu, and Ken Mai. 2012. Error Patterns in MLC NAND Flash Memory: Measurement, Characterization, and Analysis. In DATE."},{"key":"e_1_3_3_1_32_2","first-page":"521","volume-title":"2012 Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Cai Yu","year":"2012","unstructured":"Yu Cai, Erich\u00a0F Haratsch, Onur Mutlu, and Ken Mai. 2012. Error patterns in MLC NAND flash memory: Measurement, characterization, and analysis. In 2012 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 521\u2013526."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2012.6378623"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"HM Cao F Liu Q Wang ZC Du L Jin and ZL Huo. 2022. An efficient built-in error detection methodology with fast page-oriented data comparison in 3D NAND flash memories. Electronics Letters 58 12 (2022) 483\u2013485.","DOI":"10.1049\/ell2.12484"},{"key":"e_1_3_3_1_35_2","unstructured":"Chi-Min Chan Chunpu Xu Ruibin Yuan Hongyin Luo Wei Xue Yike Guo and Jie Fu. 2024. Rq-rag: Learning to refine queries for retrieval augmented generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.00610 (2024)."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/276304.276336"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Li-Pin Chang. 2010. A hybrid approach to NAND-flash-based solid-state disks. IEEE Trans. Comput. 59 10 (2010) 1337\u20131349.","DOI":"10.1109\/TC.2010.14"},{"key":"e_1_3_3_1_38_2","unstructured":"Harrison Chase. 2022. LangChain. https:\/\/github.com\/langchain-ai\/langchain"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-tutorials.8"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29728"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2024. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arxiv:https:\/\/arXiv.org\/abs\/2402.03216\u00a0[cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_3_1_42_2","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 neighborhood search. Advances in Neural Information Processing Systems 34 (2021) 5199\u20135212."},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557098"},{"key":"e_1_3_3_1_44_2","unstructured":"Wenhu Chen Xinyi Wang and William\u00a0Yang Wang. 2021. A dataset for answering time-sensitive questions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.06314 (2021)."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"Qinyuan Cheng Xiaonan Li Shimin Li Qin Zhu Zhangyue Yin Yunfan Shao Linyang Li Tianxiang Sun Hang Yan and Xipeng Qiu. 2024. Unified Active Retrieval for Retrieval Augmented Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.12534 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.999"},{"key":"e_1_3_3_1_46_2","unstructured":"Xin Cheng Di Luo Xiuying Chen Lemao Liu Dongyan Zhao and Rui Yan. 2024. Lift yourself up: Retrieval-augmented text generation with self-memory. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_47_2","volume-title":"WoNDP","author":"Cho Benjamin\u00a0Y","year":"2013","unstructured":"Benjamin\u00a0Y Cho, Won\u00a0Seob Jeong, Doohwan Oh, and Won\u00a0Woo Ro. 2013. XSD: Accelerating MapReduce by Harnessing the GPU inside an SSD. In WoNDP."},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9366054"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651341"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Taehee Cho Yeong-Taek Lee Eun-Cheol Kim Jin-Wook Lee Sunmi Choi Seungjae Lee Dong-Hwan Kim Wook-Ghee Han Young-Ho Lim Jae-Duk Lee et\u00a0al. 2001. A Dual-Mode NAND Flash Memory: 1-Gb Multilevel and High-Performance 512-Mb Single-Level Modes. JSSC (2001).","DOI":"10.1109\/4.962291"},{"key":"e_1_3_3_1_51_2","volume-title":"ISSCC","author":"Cho Wanik","year":"2022","unstructured":"Wanik Cho, Jongseok Jung, Jongwoo Kim, Junghoon Ham, Sangkyu Lee, Yujong Noh, Dauni Kim, Wanseob Lee, Kayoung Cho, Kwanho Kim, et\u00a0al. 2022. A 1-Tb, 4b\/Cell, 176-Stacked-WL 3D-NAND Flash Memory with Improved Read Latency and a 14.8 Gb\/mm2 Density. In ISSCC."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731785"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415769"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3208040.3208048"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220622"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Jack Choquette Wishwesh Gandhi Olivier Giroux Nick Stam and Ronny Krashinsky. 2021. Nvidia a100 tensor core gpu: Performance and innovation. IEEE Micro 41 2 (2021) 29\u201335.","DOI":"10.1109\/MM.2021.3061394"},{"key":"e_1_3_3_1_57_2","unstructured":"Ashish Chouhan and Michael Gertz. 2024. LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.16295 (2024)."},{"key":"e_1_3_3_1_58_2","unstructured":"CMU-SAFARI. 2015. Ramulator. https:\/\/github.com\/CMU-SAFARI\/ramulator.git."},{"key":"e_1_3_3_1_59_2","unstructured":"Cohere. 2023. Introducing Embed v3. https:\/\/cohere.com\/blog\/introducing-embed-v3"},{"key":"e_1_3_3_1_60_2","unstructured":"Cohere. 2024. beir-embed-english-v3. https:\/\/huggingface.co\/datasets\/Cohere\/beir-embed-english-v3"},{"key":"e_1_3_3_1_61_2","unstructured":"Cohere. 2024. wikipedia-2023-11-embed-multilingual-v3. https:\/\/huggingface.co\/datasets\/Cohere\/wikipedia-2023-11-embed-multilingual-v3"},{"key":"e_1_3_3_1_62_2","unstructured":"Cohere. 2024. wikipedia-2023-11-embed-multilingual-v3-int8-binary. https:\/\/huggingface.co\/datasets\/Cohere\/wikipedia-2023-11-embed-multilingual-v3-int8-binary"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"Christian\u00a0Monzio Compagnoni Akira Goda Alessandro\u00a0S Spinelli Peter Feeley Andrea\u00a0L Lacaita and Angelo Visconti. 2017. Reviewing the evolution of the NAND flash technology. Proc. IEEE 105 9 (2017) 1609\u20131633.","DOI":"10.1109\/JPROC.2017.2665781"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564420"},{"key":"e_1_3_3_1_65_2","unstructured":"Korn\u00e9l Csernai. 2017. First Quora Dataset Release: Question Pairs. https:\/\/quoradata.quora.com\/First-Quora-Dataset-Release-Question-Pairs"},{"key":"e_1_3_3_1_66_2","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.08691 (2023)."},{"key":"e_1_3_3_1_67_2","unstructured":"Tri Dao Dan Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35 (2022) 16344\u201316359."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"crossref","unstructured":"Debendra Das\u00a0Sharma Robert Blankenship and Daniel Berger. 2024. An introduction to the compute express link (cxl) interconnect. Comput. Surveys 56 11 (2024) 1\u201337.","DOI":"10.1145\/3669900"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020578"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465295"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Magdalen Dobson Zheqi Shen Guy\u00a0E. Blelloch Laxman Dhulipala Yan Gu Harsha\u00a0Vardhan Simhadri and Yihan Sun. 2023. Scaling Graph-Based ANNS Algorithms to Billion-Size Datasets: A Comparative Analysis. CoRR abs\/2305.04359 (2023). 10.48550\/arXiv.2305.04359 arXiv:https:\/\/arXiv.org\/abs\/2305.04359","DOI":"10.48550\/arXiv.2305.04359"},{"key":"e_1_3_3_1_72_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_73_2","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. arxiv:https:\/\/arXiv.org\/abs\/2401.08281\u00a0[cs.LG]"},{"key":"e_1_3_3_1_74_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_1_75_2","unstructured":"EleutherAI. 2021. GPT-J 6B. https:\/\/huggingface.co\/EleutherAI\/gpt-j-6b"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9041948"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00028"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"crossref","unstructured":"Minghui Fang Shengpeng Ji Jialong Zuo Hai Huang Yan Xia Jieming Zhu Xize Cheng Xiaoda Yang Wenrui Liu Gang Wang et\u00a0al. 2024. ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.17507 (2024).","DOI":"10.1145\/3626772.3657905"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.5555\/645484.656397"},{"key":"e_1_3_3_1_80_2","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:https:\/\/arXiv.org\/abs\/1707.00143 (2017)."},{"key":"e_1_3_3_1_81_2","unstructured":"Anoushka Gade and Jorjeta Jetcheva. 2024. It\u2019s About Time: Incorporating Temporality in Retrieval Augmented Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.13222 (2024)."},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599782"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480078"},{"key":"e_1_3_3_1_84_2","unstructured":"Luyu Gao Xueguang Ma Jimmy Lin and Jamie Callan. 2022. Precise zero-shot dense retrieval without relevance labels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.10496 (2022)."},{"key":"e_1_3_3_1_85_2","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.10997 (2023)."},{"key":"e_1_3_3_1_86_2","unstructured":"Nika\u00a0Mansouri Ghiasi Mohammad Sadrosadati Harun Mustafa Arvid Gollwitzer Can Firtina Julien Eudine Haiyu Mao Jo\u00ebl Lindegger Meryem\u00a0Banu Cavlak Mohammed Alser et\u00a0al. 2024. MegIS: High-Performance Energy-Efficient and Low-Cost Metagenomic Analysis with In-Storage Processing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.19113 (2024)."},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"crossref","unstructured":"Saugata Ghose Tianshi Li Nastaran Hajinazar Damla\u00a0Senol Cali and Onur Mutlu. 2019. Demystifying complex workload-DRAM interactions: An experimental study. Proceedings of the ACM on Measurement and Analysis of Computing Systems 3 3 (2019) 1\u201350.","DOI":"10.1145\/3366708"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448030"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080789"},{"key":"e_1_3_3_1_91_2","unstructured":"Google. 2024. Get multimodal embeddings. https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/embeddings\/get-multimodal-embeddings"},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"crossref","unstructured":"Donghyun Gouk Miryeong Kwon Hanyeoreum Bae Sangwon Lee and Myoungsoo Jung. 2023. Memory pooling with cxl. IEEE Micro 43 2 (2023) 48\u201357.","DOI":"10.1109\/MM.2023.3237491"},{"key":"e_1_3_3_1_93_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_1_94_2","doi-asserted-by":"crossref","unstructured":"Boncheol Gu Andre\u00a0S Yoon Duck-Ho Bae Insoon Jo Jinyoung Lee Jonghyun Yoon Jeong-Uk Kang Moonsang Kwon Chanho Yoon Sangyeun Cho et\u00a0al. 2016. Biscuit: A framework for near-data processing of big data workloads. ACM SIGARCH Computer Architecture News 44 3 (2016) 153\u2013165.","DOI":"10.1145\/3007787.3001154"},{"key":"e_1_3_3_1_95_2","volume-title":"ISCA","author":"Gu Boncheol","year":"2016","unstructured":"Boncheol Gu, Andre\u00a0S. Yoon, Duck-Ho Bae, Insoon Jo, Jinyoung Lee, Jonghyun Yoon, Jeong-Uk Kang, Moonsang Kwon, Chanho Yoon, Sangyeun Cho, et\u00a0al. 2016. Biscuit: A Framework for Near-Data Processing of Big Data Workloads. In ISCA."},{"key":"e_1_3_3_1_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/1508244.1508271"},{"key":"e_1_3_3_1_97_2","unstructured":"Zvika Guz Manu Awasthi Vijay Balakrishnan Mrinmoy Ghosh Anahita Shayesteh Tameesh Suri and Samsung Semiconductor. 2014. Real-Time Analytics as the Killer Application for Processing-In-Memory. WoNDP (2014)."},{"key":"e_1_3_3_1_98_2","volume-title":"Twenty-Second International Joint Conference on Artificial Intelligence","author":"Hajebi Kiana","year":"2011","unstructured":"Kiana Hajebi, Yasin Abbasi-Yadkori, Hossein Shahbazi, and Hong Zhang. 2011. Fast approximate nearest-neighbor search with k-nearest neighbor graph. In Twenty-Second International Joint Conference on Artificial Intelligence."},{"key":"e_1_3_3_1_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_3_1_100_2","doi-asserted-by":"crossref","unstructured":"Kyuhwa Han Hyukjoong Kim and Dongkun Shin. 2019. WAL-SSD: Address remapping-based write-ahead-logging solid-state disks. IEEE Trans. Comput. 69 2 (2019) 260\u2013273.","DOI":"10.1109\/TC.2019.2947897"},{"key":"e_1_3_3_1_101_2","doi-asserted-by":"crossref","unstructured":"Weidong He Zhi Li Hao Wang Tong Xu Zhefeng Wang Baoxing Huai Nicholas\u00a0Jing Yuan and Enhong Chen. 2024. Multimodal Dialogue Systems via Capturing Context-aware Dependencies and Ordinal Information of Semantic Elements. ACM Transactions on Intelligent Systems and Technology 15 3 (2024) 1\u201325.","DOI":"10.1145\/3645099"},{"key":"e_1_3_3_1_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9366003"},{"key":"e_1_3_3_1_103_2","doi-asserted-by":"crossref","unstructured":"Charles\u00a0AR Hoare. 1962. Quicksort. The computer journal 5 1 (1962) 10\u201316.","DOI":"10.1093\/comjnl\/5.1.10"},{"key":"e_1_3_3_1_104_2","doi-asserted-by":"publisher","unstructured":"C.\u00a0A.\u00a0R. Hoare. 1961. Algorithm 65: find. Commun. ACM 4 7 (jul 1961) 321\u2013322. 10.1145\/366622.366647","DOI":"10.1145\/366622.366647"},{"key":"e_1_3_3_1_105_2","unstructured":"Connor Holmes Masahiro Tanaka Michael Wyatt Ammar\u00a0Ahmad Awan Jeff Rasley Samyam Rajbhandari Reza\u00a0Yazdani Aminabadi Heyang Qin Arash Bakhtiari Lev Kurilenko et\u00a0al. 2024. Deepspeed-fastgen: High-throughput text generation for llms via mii and deepspeed-inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.08671 (2024)."},{"key":"e_1_3_3_1_106_2","unstructured":"Abe\u00a0Bohan Hou Orion Weller Guanghui Qin Eugene Yang Dawn Lawrie Nils Holzenberger Andrew Blair-Stanek and Benjamin Van\u00a0Durme. 2024. CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.17186 (2024)."},{"key":"e_1_3_3_1_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00058"},{"key":"e_1_3_3_1_108_2","volume-title":"ISCA","author":"Huang Jian","year":"2015","unstructured":"Jian Huang, Anirudh Badam, Moinuddin\u00a0K Qureshi, and Karsten Schwan. 2015. Unified Address Translation for Memory-Mapped SSDs with Flashmap. In ISCA."},{"key":"e_1_3_3_1_109_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_3_1_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_3_1_111_2","unstructured":"Intel. 2017. Intel\u00ae Xeon\u00ae Gold Processor 5118. https:\/\/www.intel.de\/content\/www\/de\/de\/products\/sku\/120473\/intel-xeon-gold-5118-processor-16-5m-cache-2-30-ghz\/specifications.html"},{"key":"e_1_3_3_1_112_2","unstructured":"Gautier Izacard Patrick Lewis Maria Lomeli Lucas Hosseini Fabio Petroni Timo Schick Jane Dwivedi-Yu Armand Joulin Sebastian Riedel and Edouard Grave. 2023. Atlas: few-shot learning with retrieval augmented language models. J. Mach. Learn. Res. 24 1 Article 251 (Jan. 2023) 43\u00a0pages."},{"key":"e_1_3_3_1_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00034"},{"key":"e_1_3_3_1_114_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). 585\u2013600."},{"key":"e_1_3_3_1_115_2","unstructured":"Tim Jansen Yangling Tong Victoria Zevallos and Pedro\u00a0Ortiz Suarez. 2022. Perplexed by quality: A perplexity-based method for adult and harmful content detection in multilingual heterogeneous web data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.10440 (2022)."},{"key":"e_1_3_3_1_116_2","unstructured":"Suhas Jayaram\u00a0Subramanya Fnu Devvrit Harsha\u00a0Vardhan 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_3_1_117_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_1_118_2","volume-title":"FAST","author":"Jeong Jaeyong","year":"2014","unstructured":"Jaeyong Jeong, Sangwook\u00a0Shane Hahn, Sungjin Lee, and Jihong Kim. 2014. Lifetime Improvement of NAND Flash-based Storage Systems Using Dynamic Program and Erase Scaling. In FAST."},{"key":"e_1_3_3_1_119_2","unstructured":"Won\u00a0Seob Jeong Changmin Lee Keunsoo Kim Myung\u00a0Kuk Yoon Won Jeon Myoungsoo Jung and Won\u00a0Woo Ro. 2019. REACT: Scalable and High-performance Regular Expression Pattern Matching Accelerator for In-storage Processing. IEEE TPDS (2019)."},{"key":"e_1_3_3_1_120_2","doi-asserted-by":"crossref","unstructured":"Ziwei Ji Nayeon Lee Rita Frieske Tiezheng Yu Dan Su Yan Xu Etsuko Ishii Ye\u00a0Jin Bang Andrea Madotto and Pascale Fung. 2023. Survey of hallucination in natural language generation. Comput. Surveys 55 12 (2023) 1\u201338.","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_1_121_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"e_1_3_3_1_122_2","first-page":"4904","volume-title":"International conference on machine learning","author":"Jia Chao","year":"2021","unstructured":"Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021. Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning. PMLR, 4904\u20134916."},{"key":"e_1_3_3_1_123_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand et\u00a0al. 2024. Mixtral of experts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.04088 (2024)."},{"key":"e_1_3_3_1_124_2","doi-asserted-by":"crossref","unstructured":"Zhengbao Jiang Frank\u00a0F Xu Luyu Gao Zhiqing Sun Qian Liu Jane Dwivedi-Yu Yiming Yang Jamie Callan and Graham Neubig. 2023. Active retrieval augmented generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06983 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_3_1_125_2","unstructured":"Jiajie Jin Yutao Zhu Xinyu Yang Chenghao Zhang and Zhicheng Dou. 2024. FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.13576 (2024)."},{"key":"e_1_3_3_1_126_2","doi-asserted-by":"crossref","unstructured":"Insoon Jo Duck-Ho Bae Andre\u00a0S Yoon Jeong-Uk Kang Sangyeun Cho Daniel\u00a0DG Lee and Jaeheon Jeong. 2016. YourSQL: a high-performance database system leveraging in-storage computing. Proceedings of the VLDB Endowment 9 12 (2016) 924\u2013935.","DOI":"10.14778\/2994509.2994512"},{"key":"e_1_3_3_1_127_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_1_128_2","volume-title":"ISCA","author":"Jun Sang-Woo","year":"2015","unstructured":"Sang-Woo Jun, Ming Liu, Sungjin Lee, Jamey Hicks, John Ankcorn, Myron King, Shuotao Xu, et\u00a0al. 2015. BlueDBM: An Appliance for Big Data Analytics. In ISCA."},{"key":"e_1_3_3_1_129_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2016.7761588"},{"key":"e_1_3_3_1_130_2","volume-title":"ISCA","author":"Jun Sang-Woo","year":"2018","unstructured":"Sang-Woo Jun, Andy Wright, Sizhuo Zhang, Shuotao Xu, and Arvind. 2018. GraFBoost: Using Accelerated Flash Storage for External Graph Analytics. In ISCA."},{"key":"e_1_3_3_1_131_2","volume-title":"Middleware","author":"Jung Myoungsoo","year":"2012","unstructured":"Myoungsoo Jung, Ramya Prabhakar, and Mahmut\u00a0Taylan Kandemir. 2012. Taking Garbage Collection Overheads Off the Critical Path in SSDs. In Middleware."},{"key":"e_1_3_3_1_132_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480109"},{"key":"e_1_3_3_1_133_2","doi-asserted-by":"crossref","unstructured":"Wonkyung Kang Dongkun Shin and Sungjoo Yoo. 2017. Reinforcement learning-assisted garbage collection to mitigate long-tail latency in SSD. ACM Transactions on Embedded Computing Systems (TECS) 16 5s (2017) 1\u201320.","DOI":"10.1145\/3126537"},{"key":"e_1_3_3_1_134_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2013.6558444"},{"key":"e_1_3_3_1_135_2","unstructured":"Jungo Kasai Keisuke Sakaguchi Ronan Le\u00a0Bras Akari Asai Xinyan Yu Dragomir Radev Noah\u00a0A Smith Yejin Choi Kentaro Inui et\u00a0al. 2024. REALTIME QA: what\u2019s the answer right now? Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_136_2","unstructured":"Nirant Kasliwal. 2023. Binary Quantization - Vector Search 40x Faster. https:\/\/qdrant.tech\/articles\/binary-quantization\/"},{"key":"e_1_3_3_1_137_2","doi-asserted-by":"crossref","unstructured":"Kimberly Keeton David\u00a0A Patterson and Joseph\u00a0M Hellerstein. 1998. A Case for Intelligent Disks (IDISKs). SIGMOD Rec. (1998).","DOI":"10.1145\/290593.290602"},{"key":"e_1_3_3_1_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365777"},{"key":"e_1_3_3_1_139_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_1_140_2","doi-asserted-by":"crossref","unstructured":"Chulbum Kim Jinho Ryu Taesung Lee Hyunggon Kim Jaewoo Lim Jaeyong Jeong Seonghwan Seo Hongsoo Jeon Bokeun Kim Inyoul Lee et\u00a0al. 2012. A 21 nm high performance 64 Gb MLC NAND flash memory with 400 MB\/s asynchronous toggle DDR interface. IEEE Journal of Solid-State Circuits 47 4 (2012) 981\u2013989.","DOI":"10.1109\/JSSC.2012.2185341"},{"key":"e_1_3_3_1_141_2","unstructured":"Gangwoo Kim Sungdong Kim Byeongguk Jeon Joonsuk Park and Jaewoo Kang. 2023. Tree of clarifications: Answering ambiguous questions with retrieval-augmented large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.14696 (2023)."},{"key":"e_1_3_3_1_142_2","doi-asserted-by":"crossref","unstructured":"Jiho Kim Myoungsoo Jung and John Kim. 2021. Decoupled SSD: Reducing Data Movement on NAND-Based Flash SSD. IEEE CAL (2021).","DOI":"10.1109\/LCA.2021.3118688"},{"key":"e_1_3_3_1_143_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071024"},{"key":"e_1_3_3_1_144_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00038"},{"key":"e_1_3_3_1_145_2","doi-asserted-by":"crossref","unstructured":"Ji-Hoon Kim Yeo-Reum Park Jaeyoung Do Soo-Young Ji and Joo-Young Kim. 2022. Accelerating large-scale graph-based nearest neighbor search on a computational storage platform. IEEE Trans. Comput. 72 1 (2022) 278\u2013290.","DOI":"10.1109\/TC.2022.3155956"},{"key":"e_1_3_3_1_146_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01318"},{"key":"e_1_3_3_1_147_2","doi-asserted-by":"publisher","DOI":"10.1145\/3409963.3410501"},{"key":"e_1_3_3_1_148_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731640"},{"key":"e_1_3_3_1_149_2","doi-asserted-by":"crossref","unstructured":"Sungchan Kim Hyunok Oh Chanik Park Sangyeun Cho Sang-Won Lee and Bongki Moon. 2016. In-storage processing of database scans and joins. Information Sciences 327 (2016) 183\u2013200.","DOI":"10.1016\/j.ins.2015.07.056"},{"key":"e_1_3_3_1_150_2","unstructured":"Sungchan Kim Hyunok Oh Chanik Park Sangyeun Cho Sang-Won Lee and Bongki Moon. 2016. In-Storage Processing of Database Scans and Joins. Information Sciences (2016)."},{"key":"e_1_3_3_1_151_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Weikun Yang and Onur Mutlu. 2015. Ramulator: A fast and extensible DRAM simulator. IEEE Computer architecture letters 15 1 (2015) 45\u201349.","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_1_152_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124553"},{"key":"e_1_3_3_1_153_2","doi-asserted-by":"crossref","unstructured":"Toshiyuki Kouchi Mami Kakoi Noriyasu Kumazaki Akio Sugahara Akihiro Imamoto Yasufumi Kajiyama Yuri Terada Bushnaq Sanad Naoaki Kanagawa Takuyo Kodama et\u00a0al. 2020. A 128gb 1-bit\/cell 96-word-line-layer 3d flash memory to improve the random read latency with tprog= 75 \u03bc s and tr= 4 \u03bc s. IEEE Journal of Solid-State Circuits 56 1 (2020) 225\u2013234.","DOI":"10.1109\/JSSC.2020.3028393"},{"key":"e_1_3_3_1_154_2","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276877"},{"key":"e_1_3_3_1_155_2","doi-asserted-by":"crossref","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Olivia Redfield Michael Collins Ankur Parikh Chris Alberti Danielle Epstein Illia Polosukhin Jacob Devlin Kenton Lee et\u00a0al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics 7 (2019) 453\u2013466.","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_3_1_156_2","unstructured":"Woosuk Kwon Zhuohan Li Siyuan Zhuang Ying Sheng Lianmin Zheng Cody Yu Joey Gonzalez Hao Zhang and Ion Stoica. 2023. vllm: Easy fast and cheap llm serving with pagedattention. See https:\/\/vllm. ai\/(accessed 9 August 2023) (2023)."},{"key":"e_1_3_3_1_157_2","unstructured":"Jakub L\u00e1la Odhran O\u2019Donoghue Aleksandar Shtedritski Sam Cox Samuel\u00a0G Rodriques and Andrew\u00a0D White. 2023. Paperqa: Retrieval-augmented generative agent for scientific research. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.07559 (2023)."},{"key":"e_1_3_3_1_158_2","unstructured":"LangChain. 2023. Text Splitters. https:\/\/python.langchain.com\/v0.1\/docs\/modules\/data_connection\/document_transformers\/"},{"key":"e_1_3_3_1_159_2","unstructured":"Chankyu Lee Rajarshi Roy Mengyao Xu Jonathan Raiman Mohammad Shoeybi Bryan Catanzaro and Wei Ping. 2024. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17428 (2024)."},{"key":"e_1_3_3_1_160_2","doi-asserted-by":"crossref","unstructured":"Dusol Lee Duwon Hong Wonil Choi and Jihong Kim. 2022. MQSim-E: An Enterprise SSD Simulator. IEEE Computer Architecture Letters 21 1 (2022) 13\u201316.","DOI":"10.1109\/LCA.2022.3144773"},{"key":"e_1_3_3_1_161_2","unstructured":"Jinhyuk Lee Zhuyun Dai Xiaoqi Ren Blair Chen Daniel Cer Jeremy\u00a0R Cole Kai Hui Michael Boratko Rajvi Kapadia Wen Ding et\u00a0al. 2024. Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.20327 (2024)."},{"key":"e_1_3_3_1_162_2","unstructured":"Junghee Lee Youngjae Kim Galen\u00a0M Shipman Sarp Oral and Jongman Kim. 2013. Preemptible I\/O Scheduling of Garbage Collection for Solid State Drives. IEEE TCAD (2013)."},{"key":"e_1_3_3_1_163_2","unstructured":"Joo\u00a0Hwan Lee Hui Zhang Veronica Lagrange Praveen Krishnamoorthy Xiaodong Zhao and Yang\u00a0Seok Ki. 2020. SmartSSD: FPGA Accelerated Near-Storage Data Analytics on SSD. IEEE CAL (2020)."},{"key":"e_1_3_3_1_164_2","volume-title":"ISSCC","author":"Lee Seungjae","year":"2004","unstructured":"Seungjae Lee, Young-Taek Lee, Wook-Kee Han, Dong-Hwan Kim, Moo-Sung Kim, Seung-Hyun Moon, Hyun\u00a0Chul Cho, Jung-Woo Lee, Dae-Seok Byeon, Young-Ho Lim, et\u00a0al. 2004. A 3.3V 4Gb Four-Level NAND Flash Memory with 90nm CMOS Technology. In ISSCC."},{"key":"e_1_3_3_1_165_2","volume-title":"Open Source Strikes Bread - New Fluffy Embeddings Model","author":"Lee Sean","year":"2024","unstructured":"Sean Lee, Aamir Shakir, Darius Koenig, and Julius Lipp. 2024. Open Source Strikes Bread - New Fluffy Embeddings Model. https:\/\/www.mixedbread.ai\/blog\/mxbai-embed-large-v1"},{"key":"e_1_3_3_1_166_2","unstructured":"Nancy Leong Sachit Chandra and Hounien Chen. 2008. Random Cache Read Using a Double Memory. US Patent 7 423 915."},{"key":"e_1_3_3_1_167_2","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\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020) 9459\u20139474."},{"key":"e_1_3_3_1_168_2","volume-title":"USENIX ATC","author":"Li Cangyuan","year":"2021","unstructured":"Cangyuan Li, Ying Wang, Cheng Liu, Shengwen Liang, Huawei Li, and Xiaowei Li. 2021. GLIST: Towards In-Storage Graph Learning. In USENIX ATC."},{"key":"e_1_3_3_1_169_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_3_1_170_2","unstructured":"Huayang Li Yixuan Su Deng Cai Yan Wang and Lemao Liu. 2022. A survey on retrieval-augmented text generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.01110 (2022)."},{"key":"e_1_3_3_1_171_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467101"},{"key":"e_1_3_3_1_172_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_3_3_1_173_2","doi-asserted-by":"crossref","unstructured":"Wen Li Ying Zhang Yifang Sun Wei Wang Mingjie Li Wenjie Zhang and Xuemin Lin. 2019. Approximate nearest neighbor search on high dimensional data\u2014experiments analyses and improvement. IEEE Transactions on Knowledge and Data Engineering 32 8 (2019) 1475\u20131488.","DOI":"10.1109\/TKDE.2019.2909204"},{"key":"e_1_3_3_1_174_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465322"},{"key":"e_1_3_3_1_175_2","doi-asserted-by":"publisher","DOI":"10.14778\/2732951.2732965"},{"key":"e_1_3_3_1_176_2","unstructured":"Zehan Li Xin Zhang Yanzhao Zhang Dingkun Long Pengjun Xie and Meishan Zhang. 2023. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.03281 (2023)."},{"key":"e_1_3_3_1_177_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00035"},{"key":"e_1_3_3_1_178_2","volume-title":"USENIX ATC","author":"Liang Shengwen","year":"2019","unstructured":"Shengwen Liang, Ying Wang, Youyou Lu, Zhe Yang, Huawei Li, and Xiaowei Li. 2019. Cognitive SSD: A Deep Learning Engine for In-Storage Data Retrieval. In USENIX ATC."},{"key":"e_1_3_3_1_179_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530560"},{"key":"e_1_3_3_1_180_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia53811.2021.9641965"},{"key":"e_1_3_3_1_181_2","doi-asserted-by":"publisher","DOI":"10.1109\/SNAPI.2010.9"},{"key":"e_1_3_3_1_182_2","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et\u00a0al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.19437 (2024)."},{"key":"e_1_3_3_1_183_2","doi-asserted-by":"publisher","unstructured":"Jerry Liu. 2022. LlamaIndex. 10.5281\/zenodo.1234","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_3_1_184_2","unstructured":"Ting Liu Andrew Moore Ke Yang and Alexander Gray. 2004. An investigation of practical approximate nearest neighbor algorithms. Advances in neural information processing systems 17 (2004)."},{"key":"e_1_3_3_1_185_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-5053-7_5"},{"key":"e_1_3_3_1_186_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30232"},{"key":"e_1_3_3_1_187_2","doi-asserted-by":"publisher","DOI":"10.1142\/9789811286421_0002"},{"key":"e_1_3_3_1_188_2","unstructured":"Shuai Lu Nan Duan Hojae Han Daya Guo Seung-won Hwang and Alexey Svyatkovskiy. 2022. Reacc: A retrieval-augmented code completion framework. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.07722 (2022)."},{"key":"e_1_3_3_1_189_2","doi-asserted-by":"crossref","unstructured":"Shyue-Kung Lu Shang-Xiu Zhong and Masaki Hashizume. 2018. Fault Leveling Techniques for Yield and Reliability Enhancement of NAND Flash Memories. Journal of Electronic Testing 34 (2018) 559\u2013570.","DOI":"10.1007\/s10836-018-5752-7"},{"key":"e_1_3_3_1_190_2","unstructured":"Macronix. 2013. Technical Note: Improving NAND Throughput with Two-Plane and Cache Operations. https:\/\/www.macronix.com\/Lists\/ApplicationNote\/Attachments\/1907\/AN0268V1_Improving%20NAND%20Throughput%20with%20Two-Plane%20and%20Cache%20Operations.pdf."},{"key":"e_1_3_3_1_191_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310321"},{"key":"e_1_3_3_1_192_2","doi-asserted-by":"crossref","unstructured":"Hosam\u00a0M Mahmoud Reza Modarres and Robert\u00a0T Smythe. 1995. Analysis of quickselect: An algorithm for order statistics. RAIRO-Theoretical Informatics and Applications 29 4 (1995) 255\u2013276.","DOI":"10.1051\/ita\/1995290402551"},{"key":"e_1_3_3_1_193_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358320"},{"key":"e_1_3_3_1_194_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358320"},{"key":"e_1_3_3_1_195_2","doi-asserted-by":"crossref","unstructured":"Yury Malkov Alexander Ponomarenko Andrey Logvinov and Vladimir Krylov. 2014. Approximate nearest neighbor algorithm based on navigable small world graphs. Information Systems 45 (2014) 61\u201368.","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_3_3_1_196_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_1_197_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_3_1_198_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638475"},{"key":"e_1_3_3_1_199_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507702"},{"key":"e_1_3_3_1_200_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507702"},{"key":"e_1_3_3_1_201_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43458-7_34"},{"key":"e_1_3_3_1_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"e_1_3_3_1_203_2","unstructured":"Rui Meng Ye Liu Shafiq\u00a0Rayhan Joty Caiming Xiong Yingbo Zhou and Semih Yavuz. 2024. Sfrembedding-mistral: enhance text retrieval with transfer learning. Salesforce AI Research Blog 3 (2024)."},{"key":"e_1_3_3_1_204_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-9431-5"},{"key":"e_1_3_3_1_205_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-9431-5"},{"key":"e_1_3_3_1_206_2","unstructured":"Microchip. 2022. Microchip 16-Channel PCIe Gen 5 Enterprise NVMe SSD Controller https:\/\/www.microchip.com\/en-us\/about\/news-releases\/products\/highest-performance-16-channel-pcie-gen-5-enterprise-nvme-ssd-controller."},{"key":"e_1_3_3_1_207_2","unstructured":"Micron. 2009. NAND Flash Memory Data Sheet: MT29F16G08ABABA MT29F32G-08AFABA MT29F64G08A[J\/K\/M]ABA MT29F128G08AUABA MT29F16G-08ABCBB MT29F32G08AECBB MT29F64G08A[K\/M]CBB MT29F128G-08AUCBB."},{"key":"e_1_3_3_1_208_2","unstructured":"Micron. 2023. 9400 NVMe\u2122 SSD. https:\/\/www.micron.com\/products\/storage\/ssd\/data-center-ssd\/9400-ssd"},{"key":"e_1_3_3_1_209_2","unstructured":"Micron. 2025. DDR4 SDRAM. https:\/\/www.micron.com\/products\/memory\/dram-components\/ddr4-sdram"},{"key":"e_1_3_3_1_210_2","unstructured":"Microsoft. 2024. Binary quantization in Azure AI Search: optimized storage and faster search. https:\/\/techcommunity.microsoft.com\/blog\/azure-ai-services-blog\/binary-quantization-in-azure-ai-search-optimized-storage-and-faster-search\/4221918"},{"key":"e_1_3_3_1_211_2","unstructured":"Microsoft. 2024. Multimodal embeddings (version 4.0). https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/computer-vision\/concept-image-retrieval"},{"key":"e_1_3_3_1_212_2","unstructured":"Niklas Muennighoff Hongjin Su Liang Wang Nan Yang Furu Wei Tao Yu Amanpreet Singh and Douwe Kiela. 2024. Generative representational instruction tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.09906 (2024)."},{"key":"e_1_3_3_1_213_2","doi-asserted-by":"crossref","unstructured":"Niklas Muennighoff Nouamane Tazi Lo\u00efc Magne and Nils Reimers. 2022. MTEB: Massive text embedding benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.07316 (2022).","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_3_1_214_2","doi-asserted-by":"crossref","unstructured":"Javier\u00a0Vargas Munoz Marcos\u00a0A Gon\u00e7alves Zanoni Dias and Ricardo da\u00a0S Torres. 2019. Hierarchical clustering-based graphs for large scale approximate nearest neighbor search. Pattern Recognition 96 (2019) 106970.","DOI":"10.1016\/j.patcog.2019.106970"},{"key":"e_1_3_3_1_215_2","volume-title":"ISCA","author":"Nadig Rakesh","year":"2023","unstructured":"Rakesh Nadig, Mohammad Sadrosadati, Haiyu Mao, Nika\u00a0Mansouri Ghiasi, Arash Tavakkol, Jisung Park, Hamid Sarbazi-Azad, Juan\u00a0G\u00f3mez Luna, and Onur Mutlu. 2023. Venice: Improving Solid-State Drive Parallelism at Low Cost via Conflict-Free Accesses. In ISCA."},{"key":"e_1_3_3_1_216_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00035"},{"key":"e_1_3_3_1_217_2","unstructured":"Rodrigo Nogueira Wei Yang Kyunghyun Cho and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1910.14424 (2019)."},{"key":"e_1_3_3_1_218_2","unstructured":"NVIDIA Corp.2023. NVIDIA H100. https:\/\/www.nvidia.com\/en-us\/data-center\/h100\/."},{"key":"e_1_3_3_1_219_2","unstructured":"nvmcommands 2024. NVM Command Set Specification Revision 1.1."},{"key":"e_1_3_3_1_220_2","volume-title":"IDEAS","author":"O\u2019Neil Elizabeth","year":"2007","unstructured":"Elizabeth O\u2019Neil, Patrick O\u2019Neil, and Kesheng Wu. 2007. Bitmap Index Design Choices and their Performance Implications. In IDEAS."},{"key":"e_1_3_3_1_221_2","unstructured":"Hiroyuki Ootomo Akira Naruse Corey Nolet Ray Wang Tamas Feher and Yong Wang. 2023. Cagra: Highly parallel graph construction and approximate nearest neighbor search for gpus. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.15136 (2023)."},{"key":"e_1_3_3_1_222_2","volume-title":"New embedding models and API updates","year":"2024","unstructured":"OpenAI. 2024. New embedding models and API updates. https:\/\/openai.com\/index\/new-embedding-models-and-api-updates\/"},{"key":"e_1_3_3_1_223_2","unstructured":"OpenAI. 2025. ChatGPT. https:\/\/chatgpt.com\/."},{"key":"e_1_3_3_1_224_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403280"},{"key":"e_1_3_3_1_225_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00069"},{"key":"e_1_3_3_1_226_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_1_227_2","doi-asserted-by":"crossref","unstructured":"Shuyi Pei Jing Yang and Qing Yang. 2019. REGISTOR: A Platform for Unstructured Data Processing inside SSD Storage. ACM TOS (2019).","DOI":"10.1145\/3310149"},{"key":"e_1_3_3_1_228_2","unstructured":"Ben Perach Ronny Ronen Benny Kimelfeld and Shahar Kvatinsky. 2022. PIMDB: Understanding Bulk-Bitwise Processing In-Memory Through Database Analytics. arXiv:https:\/\/arXiv.org\/abs\/2203.10486 (2022)."},{"key":"e_1_3_3_1_229_2","unstructured":"Malte Pietsch Timo M\u00f6ller Bogdan Kostic Julian Risch Massimiliano Pippi Mayank Jobanputra Sara Zanzottera Silvano Cerza Vladimir Blagojevic Thomas Stadelmann Tanay Soni and Sebastian Lee. 2019. Haystack: the end-to-end NLP framework for pragmatic builders. https:\/\/github.com\/deepset-ai\/haystack"},{"key":"e_1_3_3_1_230_2","doi-asserted-by":"crossref","unstructured":"Mykhailo Poliakov and Nadiya Shvai. 2024. Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.13213 (2024).","DOI":"10.1007\/978-3-031-81372-6_25"},{"key":"e_1_3_3_1_231_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461648.3463843"},{"key":"e_1_3_3_1_232_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676674"},{"key":"e_1_3_3_1_233_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707264"},{"key":"e_1_3_3_1_234_2","unstructured":"Zackary Rackauckas. 2024. Rag-fusion: a new take on retrieval-augmented generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.03367 (2024)."},{"key":"e_1_3_3_1_235_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_1_236_2","doi-asserted-by":"crossref","unstructured":"Vatsal Raina and Mark Gales. 2024. Question-Based Retrieval using Atomic Units for Enterprise RAG. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.12363 (2024).","DOI":"10.18653\/v1\/2024.fever-1.25"},{"key":"e_1_3_3_1_237_2","doi-asserted-by":"crossref","unstructured":"Md Raquibuzzaman Aleksandar Milenkovic and Biswajit Ray. 2022. Intrablock wear leveling to counter layer-to-layer endurance variation of 3-D NAND flash memory. IEEE Transactions on Electron Devices 70 1 (2022) 70\u201375.","DOI":"10.1109\/TED.2022.3224420"},{"key":"e_1_3_3_1_238_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_3_1_239_2","unstructured":"Redis. 2025. Redis bitmaps. https:\/\/redis.io\/docs\/data-types\/bitmaps\/."},{"key":"e_1_3_3_1_240_2","unstructured":"Nils Reimers. 2022. Cohere int8 & binary Embeddings - Scale Your Vector Database to Large Datasets. https:\/\/cohere.com\/blog\/int8-binary-embeddings"},{"key":"e_1_3_3_1_241_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_3_1_242_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"e_1_3_3_1_243_2","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\u201310684."},{"key":"e_1_3_3_1_244_2","doi-asserted-by":"crossref","unstructured":"Erik Riedel Christos Faloutsos Garth\u00a0A Gibson and David Nagle. 2001. Active Disks for Large-Scale Data Processing. Computer (2001).","DOI":"10.1109\/2.928624"},{"key":"e_1_3_3_1_245_2","unstructured":"Erik Riedel Garth Gibson and Christos Faloutsos. 1998. Active Storage for Large-Scale Data Mining and Multimedia Applications. VLDB (1998)."},{"key":"e_1_3_3_1_246_2","unstructured":"Meng* Rui Liu* Ye Rayhan\u00a0Joty Shafiq Xiong Caiming Zhou Yingbo and Yavuz Semih. 2024. SFR-Embedding-2: Advanced Text Embedding with Multi-stage Training. https:\/\/huggingface.co\/Salesforce\/SFR-Embedding-2_R"},{"key":"e_1_3_3_1_247_2","unstructured":"Samsung. 2009. 32Gb A-die NAND Flash Datasheet."},{"key":"e_1_3_3_1_248_2","unstructured":"Samsung. 2013. Samsung Solid State Drive TurboWrite Technology White Paper."},{"key":"e_1_3_3_1_249_2","unstructured":"Samsung. 2020. Samsung 128 GB DDR4 3200 LRDIMM ECC Registred. https:\/\/semiconductor.samsung.com\/dram\/module\/lrdimm\/m386aag40am3-cwe\/."},{"key":"e_1_3_3_1_250_2","unstructured":"Samsung. 2021. 980 Pro. https:\/\/semiconductor.samsung.com\/consumer-storage\/internal-ssd\/980pro\/"},{"key":"e_1_3_3_1_251_2","unstructured":"Samsung. 2021. PM9A3 NVMe PCIe SSD. https:\/\/semiconductor.samsung.com\/ssd\/datacenter-ssd\/pm9a3\/"},{"key":"e_1_3_3_1_252_2","unstructured":"Samsung. 2022. 990 Pro. https:\/\/semiconductor.samsung.com\/consumer-storage\/internal-ssd\/990-pro\/"},{"key":"e_1_3_3_1_253_2","doi-asserted-by":"crossref","unstructured":"Daniel Sanchez and Christos Kozyrakis. 2013. ZSim: Fast and accurate microarchitectural simulation of thousand-core systems. ACM SIGARCH Computer architecture news 41 3 (2013) 475\u2013486.","DOI":"10.1145\/2508148.2485963"},{"key":"e_1_3_3_1_254_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00031"},{"key":"e_1_3_3_1_255_2","volume-title":"USENIX OSDI","author":"Seshadri Sudharsan","year":"2014","unstructured":"Sudharsan Seshadri, Mark Gahagan, Sundaram Bhaskaran, Trevor Bunker, Arup De, Yanqin Jin, Yang Liu, and Steven Swanson. 2014. Willow: A User-Programmable SSD. In USENIX OSDI."},{"key":"e_1_3_3_1_256_2","doi-asserted-by":"crossref","unstructured":"Vivek Seshadri Kevin Hsieh Amirali Boroumand Donghyuk Lee Michael\u00a0A. Kozuch Onur Mutlu Phillip\u00a0B. Gibbons and Todd\u00a0C. Mowry. 2015. Fast Bulk Bitwise AND and OR in DRAM. IEEE CAL (2015).","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_3_3_1_257_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_3_1_258_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_1_259_2","unstructured":"Jay Shah Ganesh Bikshandi Ying Zhang Vijay Thakkar Pradeep Ramani and Tri Dao. 2024. Flashattention-3: Fast and accurate attention with asynchrony and low-precision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.08608 (2024)."},{"key":"e_1_3_3_1_260_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.47"},{"key":"e_1_3_3_1_261_2","unstructured":"Aamir Shakir Tom Aarsen and Sean Lee. 2024. Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval. Hugging Face Blog (2024). https:\/\/huggingface.co\/blog\/embedding-quantization."},{"key":"e_1_3_3_1_262_2","doi-asserted-by":"crossref","unstructured":"Noboru Shibata Kazushige Kanda Takahiro Shimizu Jun Nakai Osamu Nagao Naoki Kobayashi Makoto Miakashi Yasushi Nagadomi Tomoaki Nakano Takahisa Kawabe et\u00a0al. 2019. A 1.33-Tb 4-Bit\/Cell 3-D Flash Memory on a 96-Word-Line-Layer Technology. JSSC (2019).","DOI":"10.1109\/ISSCC.2019.8662443"},{"key":"e_1_3_3_1_263_2","volume-title":"ICS","author":"Shin Ji-Yong","year":"2009","unstructured":"Ji-Yong Shin, Zeng-Lin Xia, Ning-Yi Xu, Rui Gao, Xiong-Fei Cai, Seungryoul Maeng, and Feng-Hsiung Hsu. 2009. FTL Design Exploration in Reconfigurable High-Performance SSD for Server Applications. In ICS."},{"key":"e_1_3_3_1_264_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.08053 (2019)."},{"key":"e_1_3_3_1_265_2","unstructured":"Harsha Simhadri et\u00a0al. 2023. Big ANN Benchmarks. https:\/\/github.com\/harsha-simhadri\/big-ann-benchmarks\/tree\/main"},{"key":"e_1_3_3_1_266_2","first-page":"177","volume-title":"NeurIPS 2021 Competitions and Demonstrations Track","author":"Simhadri Harsha\u00a0Vardhan","year":"2022","unstructured":"Harsha\u00a0Vardhan Simhadri, George Williams, Martin Aum\u00fcller, Matthijs Douze, Artem Babenko, Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamny, Gopal Srinivasa, et\u00a0al. 2022. Results of the NeurIPS\u201921 challenge on billion-scale approximate nearest neighbor search. In NeurIPS 2021 Competitions and Demonstrations Track. PMLR, 177\u2013189."},{"key":"e_1_3_3_1_267_2","doi-asserted-by":"crossref","unstructured":"Kang-Deog Suh Byung-Hoon Suh Young-Ho Lim Jin-Ki Kim Young-Joon Choi Yong-Nam Koh Sung-Soo Lee Suk-Chon Kwon Byung-Soon Choi Jin-Sun Yum Jung-Hyuk Choi Jang-Rae Kim and Hyung-Kyu Lim. 1995. A 3.3 V 32 Mb NAND Flash Memory with Incremental Step Pulse Programming Scheme. JSSC (1995).","DOI":"10.1109\/4.475701"},{"key":"e_1_3_3_1_268_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575744"},{"key":"e_1_3_3_1_269_2","unstructured":"Philip Sun. 2020. Announcing ScaNN: Efficient Vector Similarity Search. https:\/\/research.google\/blog\/announcing-scann-efficient-vector-similarity-search\/"},{"key":"e_1_3_3_1_270_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00128"},{"key":"e_1_3_3_1_271_2","volume-title":"FAST","author":"Tavakkol Arash","year":"2018","unstructured":"Arash Tavakkol, Juan G\u00f3mez-Luna, Mohammad Sadrosadati, Saugata Ghose, and Onur Mutlu. 2018. MQSim: A Framework for Enabling Realistic Studies of Modern Multi-Queue SSD Devices. In FAST."},{"key":"e_1_3_3_1_272_2","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew\u00a0M Dai Anja Hauth Katie Millican et\u00a0al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.11805 (2023)."},{"key":"e_1_3_3_1_273_2","unstructured":"Gemini Team Petko Georgiev Ving\u00a0Ian Lei Ryan Burnell Libin Bai Anmol Gulati Garrett Tanzer Damien Vincent Zhufeng Pan Shibo Wang et\u00a0al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.05530 (2024)."},{"key":"e_1_3_3_1_274_2","unstructured":"Nandan Thakur Nils Reimers and Jimmy Lin. 2023. Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.11498 (2023)."},{"key":"e_1_3_3_1_275_2","unstructured":"Nandan Thakur Nils Reimers Andreas R\u00fcckl\u00e9 Abhishek Srivastava and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.08663 (2021)."},{"key":"e_1_3_3_1_276_2","unstructured":"Ravi Theja. 2023. Evaluating the Ideal Chunk Size for a RAG System using LlamaIndex. https:\/\/www.llamaindex.ai\/blog\/evaluating-the-ideal-chunk-size-for-a-rag-system-using-llamaindex-6207e5d3fec5"},{"key":"e_1_3_3_1_277_2","doi-asserted-by":"crossref","unstructured":"James Thorne Andreas Vlachos Christos Christodoulopoulos and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05355 (2018).","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_3_1_278_2","first-page":"1135","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). 1135\u20131150."},{"key":"e_1_3_3_1_279_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10665247"},{"key":"e_1_3_3_1_280_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10665247"},{"key":"e_1_3_3_1_281_2","volume-title":"FAST","author":"Tiwari Devesh","year":"2013","unstructured":"Devesh Tiwari, Simona Boboila, Sudharshan Vazhkudai, Youngjae Kim, Xiaosong Ma, Peter Desnoyers, and Yan Solihin. 2013. Active Flash: Towards Energy-Efficient, In-Situ Data Analytics on Extreme-Scale Machines. In FAST."},{"key":"e_1_3_3_1_282_2","volume-title":"HotPower","author":"Tiwari Devesh","year":"2012","unstructured":"Devesh Tiwari, Sudharshan\u00a0S Vazhkudai, Youngjae Kim, Xiaosong Ma, Simona Boboila, and Peter\u00a0J Desnoyers. 2012. Reducing Data Movement Costs Using Energy-Ef\ufb01cient, Active Computation on SSD. In HotPower."},{"key":"e_1_3_3_1_283_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00195"},{"key":"e_1_3_3_1_284_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMPDP.2019.8671589"},{"key":"e_1_3_3_1_285_2","unstructured":"Toshiba. 2012. NAND Memory Toggle DDR1.0 Technical Data Sheet."},{"key":"e_1_3_3_1_286_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_1_287_2","doi-asserted-by":"crossref","unstructured":"Shivani Tripathy and Manoranjan Satpathy. 2022. SSD internal cache management policies: A survey. Journal of Systems Architecture 122 (2022) 102334.","DOI":"10.1016\/j.sysarc.2021.102334"},{"key":"e_1_3_3_1_288_2","doi-asserted-by":"crossref","unstructured":"Ozan Unlu Jiyeon Shin Charlotte\u00a0J Mailly Michael\u00a0F Oates Michela\u00a0R Tucci Matthew Varugheese Kavishwar Wagholikar Fei Wang Benjamin\u00a0M Scirica Alexander\u00a0J Blood et\u00a0al. 2024. Retrieval-Augmented Generation\u2013Enabled GPT-4 for Clinical Trial Screening. NEJM AI (2024) AIoa2400181.","DOI":"10.1056\/AIoa2400181"},{"key":"e_1_3_3_1_289_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657931"},{"key":"e_1_3_3_1_290_2","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545087"},{"key":"e_1_3_3_1_291_2","doi-asserted-by":"crossref","unstructured":"Haoyu Wang Ruirui Li Haoming Jiang Jinjin Tian Zhengyang Wang Chen Luo Xianfeng Tang Monica Cheng Tuo Zhao and Jing Gao. 2024. Blendfilter: Advancing retrieval-augmented large language models via query generation blending and knowledge filtering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.11129 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.58"},{"key":"e_1_3_3_1_292_2","volume-title":"DaMoN","author":"Wang Jianguo","year":"2016","unstructured":"Jianguo Wang, Dongchul Park, Yang-Suk Kee, Yannis Papakonstantinou, and Steven Swanson. 2016. SSD In-Storage Computing for List Intersection. In DaMoN."},{"key":"e_1_3_3_1_293_2","unstructured":"Liang Wang Nan Yang Xiaolong Huang Binxing Jiao Linjun Yang Daxin Jiang Rangan Majumder and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.03533 (2022)."},{"key":"e_1_3_3_1_294_2","unstructured":"Liang Wang Nan Yang Xiaolong Huang Linjun Yang Rangan Majumder and Furu Wei. 2023. Improving text embeddings with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.00368 (2023)."},{"key":"e_1_3_3_1_295_2","doi-asserted-by":"crossref","unstructured":"Liang Wang Nan Yang and Furu Wei. 2023. Query2doc: Query expansion with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.07678 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"e_1_3_3_1_296_2","unstructured":"Mengzhao Wang Xiaoliang Xu Qiang Yue and Yuxiang Wang. 2021. A comprehensive survey and experimental comparison of graph-based approximate nearest neighbor search. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.12631 (2021)."},{"key":"e_1_3_3_1_297_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00054"},{"key":"e_1_3_3_1_298_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616256"},{"key":"e_1_3_3_1_299_2","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303983"},{"key":"e_1_3_3_1_300_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00035"},{"key":"e_1_3_3_1_301_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00033"},{"key":"e_1_3_3_1_302_2","unstructured":"Zhiruo Wang Jun Araki Zhengbao Jiang Md\u00a0Rizwan Parvez and Graham Neubig. 2023. Learning to filter context for retrieval-augmented generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.08377 (2023)."},{"key":"e_1_3_3_1_303_2","unstructured":"Zichao Wang Weili Nie Zhuoran Qiao Chaowei Xiao Richard Baraniuk and Anima Anandkumar. 2022. Retrieval-based controllable molecule generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.11126 (2022)."},{"key":"e_1_3_3_1_304_2","unstructured":"Zheng Wang Shu\u00a0Xian Teo Jieer Ouyang Yongjun Xu and Wei Shi. 2024. M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.16420 (2024)."},{"key":"e_1_3_3_1_305_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63646-2_29"},{"key":"e_1_3_3_1_306_2","volume-title":"FAST","author":"Wu Guanying","year":"2012","unstructured":"Guanying Wu and Xubin He. 2012. Reducing SSD Read Latency via NAND Flash Program and Erase Suspension. In FAST."},{"key":"e_1_3_3_1_307_2","volume-title":"ICDE","author":"Wu Ming-Chuan","year":"1998","unstructured":"Ming-Chuan Wu and Alejandro\u00a0P Buchmann. 1998. Encoded Bitmap Indexing for Data Warehouses. In ICDE."},{"key":"e_1_3_3_1_308_2","volume-title":"ICS","author":"Wu Suzhen","year":"2016","unstructured":"Suzhen Wu, Yanping Lin, Bo Mao, and Hong Jiang. 2016. GCaR: Garbage Collection aware Cache Management with Improved Performance for Flash-based SSDs. In ICS."},{"key":"e_1_3_3_1_309_2","doi-asserted-by":"crossref","unstructured":"Chunhua Xiao Shi Qiu and Dandan Xu. 2022. PASM: Parallelism Aware Space Management strategy for hybrid SSD towards in-storage DNN training acceleration. Journal of Systems Architecture 128 (2022) 102565.","DOI":"10.1016\/j.sysarc.2022.102565"},{"key":"e_1_3_3_1_310_2","unstructured":"Guangzhi Xiong Qiao Jin Zhiyong Lu and Aidong Zhang. 2024. Benchmarking retrieval-augmented generation for medicine. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.13178 (2024)."},{"key":"e_1_3_3_1_311_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_1_312_2","unstructured":"Jinlong Xue Yayue Deng Yingming Gao and Ya Li. 2024. Retrieval Augmented Generation in Prompt-based Text-to-Speech Synthesis with Context-Aware Contrastive Language-Audio Pretraining. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.03714 (2024)."},{"key":"e_1_3_3_1_313_2","unstructured":"Ikuya Yamada Akari Asai and Hannaneh Hajishirzi. 2021. Efficient passage retrieval with hashing for open-domain question answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.00882 (2021)."},{"key":"e_1_3_3_1_314_2","doi-asserted-by":"crossref","unstructured":"Shiqin Yan Huaicheng Li Mingzhe Hao Michael\u00a0Hao Tong Swaminathan Sundararaman Andrew\u00a0A Chien and Haryadi\u00a0S Gunawi. 2017. Tiny-tail flash: Near-perfect elimination of garbage collection tail latencies in NAND SSDs. ACM Transactions on Storage (TOS) 13 3 (2017) 1\u201326.","DOI":"10.1145\/3121133"},{"key":"e_1_3_3_1_315_2","doi-asserted-by":"crossref","unstructured":"Shi-Qi Yan Jia-Chen Gu Yun Zhu and Zhen-Hua Ling. 2024. Corrective retrieval augmented generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.15884 (2024).","DOI":"10.2139\/ssrn.5267341"},{"key":"e_1_3_3_1_316_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01032"},{"key":"e_1_3_3_1_317_2","doi-asserted-by":"publisher","DOI":"10.1109\/SMARTCOMP.2014.7043841"},{"key":"e_1_3_3_1_318_2","doi-asserted-by":"publisher","DOI":"10.5555\/3357062.3357089"},{"key":"e_1_3_3_1_319_2","unstructured":"Sophia Yang. 2023. Advanced RAG 01: Small-to-Big Retrieval. https:\/\/towardsdatascience.com\/advanced-rag-01-small-to-big-retrieval-172181b396d4"},{"key":"e_1_3_3_1_320_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD63220.2024.00059"},{"key":"e_1_3_3_1_321_2","doi-asserted-by":"crossref","unstructured":"Zhilin Yang Peng Qi Saizheng Zhang Yoshua Bengio William\u00a0W Cohen Ruslan Salakhutdinov and Christopher\u00a0D Manning. 2018. HotpotQA: A dataset for diverse explainable multi-hop question answering. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1809.09600 (2018).","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_3_1_322_2","doi-asserted-by":"crossref","unstructured":"Yingbiao Yao Jinlong Fan Jie Zhou Xiaochong Kong and Nenghua Gu. 2021. HDFTL: An on-demand flash translation layer algorithm for hybrid solid state drives. IEEE Transactions on Consumer Electronics 67 1 (2021) 50\u201357.","DOI":"10.1109\/TCE.2020.3048904"},{"key":"e_1_3_3_1_323_2","unstructured":"Antonio\u00a0Jimeno Yepes Yao You Jan Milczek Sebastian Laverde and Leah Li. 2024. Financial Report Chunking for Effective Retrieval Augmented Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.05131 (2024)."},{"key":"e_1_3_3_1_324_2","first-page":"521","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo\u00a0Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A distributed serving system for { Transformer-Based} generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). 521\u2013538."},{"key":"e_1_3_3_1_325_2","unstructured":"Hao Yu Aoran Gan Kai Zhang Shiwei Tong Qi Liu and Zhaofeng Liu. 2024. Evaluation of Retrieval-Augmented Generation: A Survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.07437 (2024)."},{"key":"e_1_3_3_1_326_2","doi-asserted-by":"crossref","unstructured":"Cyril Zakka Rohan Shad Akash Chaurasia Alex\u00a0R Dalal Jennifer\u00a0L Kim Michael Moor Robyn Fong Curran Phillips Kevin Alexander Euan Ashley et\u00a0al. 2024. Almanac\u2014retrieval-augmented language models for clinical medicine. NEJM AI 1 2 (2024) AIoa2300068.","DOI":"10.1056\/AIoa2300068"},{"key":"e_1_3_3_1_327_2","doi-asserted-by":"crossref","unstructured":"Shenglai Zeng Jiankun Zhang Pengfei He Yue Xing Yiding Liu Han Xu Jie Ren Shuaiqiang Wang Dawei Yin Yi Chang et\u00a0al. 2024. The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.16893 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.267"},{"key":"e_1_3_3_1_328_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614292"},{"key":"e_1_3_3_1_329_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498443"},{"key":"e_1_3_3_1_330_2","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626866"},{"key":"e_1_3_3_1_331_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539212"},{"key":"e_1_3_3_1_332_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin et\u00a0al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022)."},{"key":"e_1_3_3_1_333_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00088"},{"key":"e_1_3_3_1_334_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219820"},{"key":"e_1_3_3_1_335_2","unstructured":"Penghao Zhao Hailin Zhang Qinhan Yu Zhengren Wang Yunteng Geng Fangcheng Fu Ling Yang Wentao Zhang and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.19473 (2024)."},{"key":"e_1_3_3_1_336_2","doi-asserted-by":"crossref","unstructured":"Wayne\u00a0Xin Zhao Jing Liu Ruiyang Ren and Ji-Rong Wen. 2024. Dense text retrieval based on pretrained language models: A survey. ACM Transactions on Information Systems 42 4 (2024) 1\u201360.","DOI":"10.1145\/3637870"},{"key":"e_1_3_3_1_337_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-industry.23"},{"key":"e_1_3_3_1_338_2","unstructured":"Zexuan Zhong Tao Lei and Danqi Chen. 2022. Training language models with memory augmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.12674 (2022)."},{"key":"e_1_3_3_1_339_2","unstructured":"Junjie Zhou Zheng Liu Shitao Xiao Bo Zhao and Yongping Xiong. 2024. VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.04292 (2024)."},{"key":"e_1_3_3_1_340_2","unstructured":"Yanqi Zhou Tao Lei Hanxiao Liu Nan Du Yanping Huang Vincent Zhao Andrew\u00a0M Dai Quoc\u00a0V Le James Laudon et\u00a0al. 2022. Mixture-of-experts with expert choice routing. Advances in Neural Information Processing Systems 35 (2022) 7103\u20137114."},{"key":"e_1_3_3_1_341_2","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741949"},{"key":"e_1_3_3_1_342_2","first-page":"187","volume-title":"19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Zhou You","year":"2021","unstructured":"You Zhou, Qiulin Wu, Fei Wu, Hong Jiang, Jian Zhou, and Changsheng Xie. 2021. { Remap-SSD} : Safely and Efficiently Exploiting { SSD} Address Remapping to Eliminate Duplicate Writes. In 19th USENIX Conference on File and Storage Technologies (FAST 21). 187\u2013202."},{"key":"e_1_3_3_1_343_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247946"},{"key":"e_1_3_3_1_344_2","doi-asserted-by":"crossref","unstructured":"Justin Zobel and Alistair Moffat. 2006. Inverted files for text search engines. ACM computing surveys (CSUR) 38 2 (2006) 6\u2013es.","DOI":"10.1145\/1132956.1132959"},{"key":"e_1_3_3_1_345_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T07:08:59Z","timestamp":1750489739000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":344,"alternative-id":["10.1145\/3695053.3731116","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731116","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}