{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T17:55:51Z","timestamp":1785952551648,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFB4503400"],"award-info":[{"award-number":["2023YFB4503400"]}],"id":[{"id":"10.13039\/501100012166","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\/3695053.3731089","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"884-898","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["HeterRAG: Heterogeneous Processing-in-Memory Acceleration for Retrieval-augmented Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2180-5428","authenticated-orcid":false,"given":"Chaoqiang","family":"Liu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3319-254X","authenticated-orcid":false,"given":"Haifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4158-5239","authenticated-orcid":false,"given":"Dan","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3927-1102","authenticated-orcid":false,"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1845-0160","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8231-2467","authenticated-orcid":false,"given":"Wenjing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6302-813X","authenticated-orcid":false,"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"265","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek\u00a0Gordon Murray, Benoit Steiner, Paul\u00a0A. Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016. TensorFlow: A System for Large-Scale Machine Learning. In Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 265\u2013283."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE59067.2024.00031"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00080"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.124"},{"key":"e_1_3_3_1_6_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 14 2 (2017) 14:1\u201314:25.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1160"},{"key":"e_1_3_3_1_8_2","first-page":"2206","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Borgeaud Sebastian","year":"2022","unstructured":"Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van\u00a0den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las\u00a0Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cassirer, Andy Brock, Michela Paganini, Geoffrey Irving, Oriol Vinyals, Simon Osindero, Karen Simonyan, Jack\u00a0W. Rae, Erich Elsen, and Laurent Sifre. 2022. Improving Language Models by Retrieving from Trillions of Tokens. In Proceedings of the International Conference on Machine Learning (ICML). 2206\u20132240."},{"key":"e_1_3_3_1_9_2","first-page":"1877","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS). 1877\u20131901."},{"key":"e_1_3_3_1_10_2","first-page":"17413","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Chen Beidi","year":"2021","unstructured":"Beidi Chen, Tri Dao, Eric Winsor, Zhao Song, Atri Rudra, and Christopher R\u00e9. 2021. Scatterbrain: Unifying Sparse and Low-rank Attention. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems (NeurIPS). 17413\u201317426."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1171"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00050"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589091"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00032"},{"key":"e_1_3_3_1_15_2","unstructured":"Mingkai Chen Tianhua Han Cheng Liu Shengwen Liang Kuai Yu Lei Dai Ziming Yuan Ying Wang Lei Zhang Huawei Li and Xiaowei Li. 2024. DRIM-ANN: An Approximate Nearest Neighbor Search Engine based on Commercial DRAM-PIMs. ArXiv Preprint arXiv:2410.15621 (2024)."},{"key":"e_1_3_3_1_16_2","unstructured":"Sitian Chen Amelie\u00a0Chi Zhou Yucheng Shi Yusen Li and Xin Yao. 2024. MemANNS: Enhancing Billion-Scale ANNS Efficiency with Practical PIM Hardware. ArXiv Preprint arXiv:2410.23805 (2024)."},{"key":"e_1_3_3_1_17_2","unstructured":"Compute Express\u00a0Link Consortium. 2024. Compute Express Link\u2122 (CXL\u2122) specification. https: \/\/computeexpresslink.org\/cxl-specification"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/800046.801649"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Jerome\u00a0H. Friedman Jon\u00a0Louis Bentley and Raphael\u00a0A. Finkel. 1977. An Algorithm for Finding Best Matches in Logarithmic Expected Time. ACM Trans. Math. Software 3 3 (1977) 209\u2013226.","DOI":"10.1145\/355744.355745"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Cong Fu Chao Xiang Changxu Wang and Deng Cai. 2019. Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph. Proceedings of the VLDB Endowment 12 5 (2019) 461\u2013474.","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_3_1_21_2","unstructured":"Galileo. 2025. \"Mastering RAG: How To Architect An Enterprise RAG System\". https:\/\/www.galileo.ai\/blog\/mastering-rag-how-to-architect-an-enterprise-rag-system"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00071"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/602259.602266"},{"key":"e_1_3_3_1_24_2","first-page":"3929","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","volume":"119","author":"Guu Kelvin","year":"2020","unstructured":"Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. Retrieval Augmented Language Model Pre-Training. In Proceedings of the International Conference on Machine Learning (ICML), Vol.\u00a0119. 3929\u20133938."},{"key":"e_1_3_3_1_25_2","first-page":"328","volume-title":"Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Ham Tae\u00a0Jun","year":"2020","unstructured":"Tae\u00a0Jun Ham, Sungjun Jung, Seonghak Kim, Young\u00a0H. Oh, Yeonhong Park, Yoonho Song, Jung-Hun Park, Sanghee Lee, Kyoung Park, Jae\u00a0W. Lee, and Deog-Kyoon Jeong. 2020. A3: Accelerating Attention Mechanisms in Neural Networks with Approximation. In Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 328\u2013341."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_1_28_2","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de Las\u00a0Casas Lisa\u00a0Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katie Millican George van\u00a0den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Jack\u00a0W. Rae Oriol Vinyals and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. ArXiv Preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin and Ting Liu. 2025. A Survey on Hallucination in Large Language Models: Principles Taxonomy Challenges and Open Questions. ACM Transactions on Information Systems 43 2 (2025) 1\u201355.","DOI":"10.1145\/3703155"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00079"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Yu Huang Long Zheng Pengcheng Yao Qinggang Wang Haifeng Liu Xiaofei Liao Hai Jin and Jingling Xue. 2022. ReaDy: A ReRAM-Based Processing-in-Memory Accelerator for Dynamic Graph Convolutional Networks. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 11 (2022) 3567\u20133578.","DOI":"10.1109\/TCAD.2022.3199152"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_3_1_33_2","unstructured":"JEDEC. 2021. DDR4 SDRAM STANDARD."},{"key":"e_1_3_3_1_34_2","unstructured":"Wenqi Jiang Marco Zeller Roger Waleffe Torsten Hoefler and Gustavo Alonso. 2023. Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models. ArXiv Preprint arXiv:2310.09949 (2023)."},{"key":"e_1_3_3_1_35_2","unstructured":"Wenqi Jiang Shuai Zhang Boran Han Jie Wang Bernie Wang and Tim Kraska. 2024. PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design. ArXiv Preprint arXiv:2403.05676 (2024)."},{"key":"e_1_3_3_1_36_2","unstructured":"Chao Jin Zili Zhang Xuanlin Jiang Fangyue Liu Xin Liu Xuanzhe Liu and Xin Jin. 2024. RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation. ArXiv Preprint arXiv:2404.12457 (2024)."},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"crossref","unstructured":"Hai Jin Dan Chen Long Zheng Yu Huang Pengcheng Yao Jin Zhao Xiaofei Liao and Wenbin Jiang. 2023. Accelerating Graph Convolutional Networks Through a PIM-Accelerated Approach. IEEE Trans. Comput. 72 9 (2023) 2628\u20132640.","DOI":"10.1109\/TC.2023.3257514"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"e_1_3_3_1_39_2","first-page":"1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA)","author":"Jouppi Norman\u00a0P.","year":"2021","unstructured":"Norman\u00a0P. Jouppi, Doe\u00a0Hyun Yoon, Matthew Ashcraft, Mark Gottscho, Thomas\u00a0B. Jablin, George Kurian, James Laudon, Sheng Li, Peter\u00a0C. Ma, Xiaoyu Ma, Thomas Norrie, Nishant Patil, Sushma Prasad, Cliff Young, Zongwei Zhou, and David\u00a0A. Patterson. 2021. Ten Lessons From Three Generations Shaped Google\u2019s TPUv4i : Industrial Product. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 1\u201314."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_3_1_41_2","unstructured":"Omar Khattab Keshav Santhanam Xiang\u00a0Lisa Li David Hall Percy Liang Christopher Potts and Matei Zaharia. 2022. Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP. ArXiv Preprint arXiv:2212.14024 (2022)."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Weikun Yang and Onur Mutlu. 2016. Ramulator: A Fast and Extensible DRAM Simulator. IEEE Computer Architecture Letters 15 1 (2016) 45\u201349.","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Olivia Redfield Michael Collins Ankur\u00a0P. Parikh Chris Alberti Danielle Epstein Illia Polosukhin Jacob Devlin Kenton Lee Kristina Toutanova Llion Jones Matthew Kelcey Ming-Wei Chang Andrew\u00a0M. Dai Jakob Uszkoreit Quoc Le and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association for Computational Linguistics 7 (2019) 452\u2013466.","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00021"},{"key":"e_1_3_3_1_49_2","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Lewis Patrick S.\u00a0H.","year":"2020","unstructured":"Patrick S.\u00a0H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems (NeurIPS). 9459\u20139474."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380600"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640376"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Wen Li Ying Zhang Yifang Sun Wei Wang Mingjie Li Wenjie Zhang and Xuemin Lin. 2020. Approximate Nearest Neighbor Search on High Dimensional Data - Experiments Analyses and Improvement. IEEE Transactions on Knowledge and Data Engineering 32 (2020) 1475\u20131488.","DOI":"10.1109\/TKDE.2019.2909204"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"crossref","unstructured":"Chaoqiang Liu Xiaofei Liao Long Zheng Yu Huang Haifeng Liu Yi Zhang Haiheng He Haoyan Huang Jingyi Zhou and Hai Jin. 2024. L-FNNG: Accelerating Large-Scale KNN Graph Construction on CPU-FPGA Heterogeneous Platform. ACM Transactions on Reconfigurable Technology and Systems 17 3 (2024) 46:1\u201346:29.","DOI":"10.1145\/3652609"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543622.3573189"},{"key":"e_1_3_3_1_56_2","unstructured":"Fei Liu Zejun Kang and Xing Han. 2024. Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models. ArXiv Preprint arXiv:2408.05933 (2024)."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589101"},{"key":"e_1_3_3_1_58_2","first-page":"52342","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Liu Zichang","year":"2023","unstructured":"Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, and Anshumali Shrivastava. 2023. Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems (NeurIPS). 52342\u201352364."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"crossref","unstructured":"Yury\u00a0A. Malkov and Dmitry\u00a0A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence 42 4 (2020) 824\u2013836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"e_1_3_3_1_61_2","unstructured":"Micron. 2017. \"Micron: System power calculator (DDR4)\". https:\/\/www.micron.com\/sales-support\/design-tools\/dram-power-calculator"},{"key":"e_1_3_3_1_62_2","first-page":"50:1\u201350:13","volume-title":"Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Moghaddam Hadi\u00a0Asghari","year":"2016","unstructured":"Hadi\u00a0Asghari Moghaddam, Young\u00a0Hoon Son, Jung\u00a0Ho Ahn, and Nam\u00a0Sung Kim. 2016. Chameleon: Versatile and practical near-DRAM acceleration architecture for large memory systems. In Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 50:1\u201350:13."},{"key":"e_1_3_3_1_63_2","unstructured":"Timothy\u00a0Prickett Morgan. 2024. He Who Can Pay Top Dollar For HBM Memory Controls AI Training. https:\/\/www.nextplatform.com\/2024\/02\/27\/he-who-can-pay-top-dollar-for-hbm-memory-controls-ai-training"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00323"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_3_1_68_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"crossref","unstructured":"Ori Ram Yoav Levine Itay Dalmedigos Dor Muhlgay Amnon Shashua Kevin Leyton-Brown and Yoav Shoham. 2023. In-Context Retrieval-Augmented Language Models. Transactions of the Association for Computational Linguistics 11 (2023) 1316\u20131331.","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"e_1_3_3_1_72_2","first-page":"2321","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems (NIPS)","author":"Shrivastava Anshumali","year":"2014","unstructured":"Anshumali Shrivastava and Ping Li. 2014. Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS). In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems (NIPS). 2321\u20132329."},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"crossref","unstructured":"Shamane Siriwardhana Rivindu Weerasekera Tharindu Kaluarachchi Elliott Wen Rajib Rana and Suranga Nanayakkara. 2023. Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering. Transactions of the Association for Computational Linguistics 11 (2023) 1\u201317.","DOI":"10.1162\/tacl_a_00530"},{"key":"e_1_3_3_1_74_2","unstructured":"Inc. Synopsys. 2024. Design Compiler\u00ae: RTL Synthesis Solution. \"https:\/\/www.synopsys.com\/\""},{"key":"e_1_3_3_1_75_2","unstructured":"LangChain Team. 2025. LangChain. https:\/\/python.langchain.com\/docs\/introduction\/"},{"key":"e_1_3_3_1_76_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit\u00a0Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric\u00a0Michael Smith Ranjan Subramanian Xiaoqing\u00a0Ellen Tan Binh Tang Ross Taylor Adina Williams Jian\u00a0Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. ArXiv Preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_3_1_77_2","unstructured":"TrendForce. 2025. DRAM Price Trends. https:\/\/www.trendforce.com\/price"},{"key":"e_1_3_3_1_78_2","unstructured":"TrendForce. 2025. Micron Alerts Customers to Price Hikes Signaling Robust 2025\u201326 Demand. https:\/\/www.trendforce.com\/news\/2025\/03\/26\/news-micron-alerts-customers-to-price-hikes-signaling-robust-2025-26-demand\/"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"e_1_3_3_1_80_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NIPS). 5998\u20136008."},{"key":"e_1_3_3_1_81_2","unstructured":"Sriram Veturi Saurabh Vaichal Reshma\u00a0Lal Jagadheesh Nafis\u00a0Irtiza Tripto and Nian Yan. 2024. RAG based Question-Answering for Contextual Response Prediction System. ArXiv Preprint arXiv:2409.03708 (2024)."},{"key":"e_1_3_3_1_82_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. 2024. Voyager: An Open-Ended Embodied Agent with Large Language Models. Transactions on Machine Learning Research 2024 (2024)."},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"crossref","unstructured":"Mengzhao Wang Xiaoliang Xu Qiang Yue and Yuxiang Wang. 2021. A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search. Proceedings of the VLDB Endowment 14 11 (2021) 1964\u20131978.","DOI":"10.14778\/3476249.3476255"},{"key":"e_1_3_3_1_84_2","unstructured":"John Ward. 2024. Memory Price Index Hits Four-and-a-Half Year High. https:\/\/intelligence.supplyframe.com\/zh\/memory-price-index-hits-four-year-high"},{"key":"e_1_3_3_1_85_2","unstructured":"Shangyu Wu Ying Xiong Yufei Cui Haolun Wu Can Chen Ye Yuan Lianming Huang Xue Liu Tei-Wei Kuo Nan Guan and Chun\u00a0Jason Xue. 2024. Retrieval-Augmented Generation for Natural Language Processing: A Survey. ArXiv Preprint arXiv:2407.13193 (2024)."},{"key":"e_1_3_3_1_86_2","first-page":"1673","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems (NIPS)","author":"Xie Cong","year":"2014","unstructured":"Cong Xie, Ling Yan, Wu-Jun Li, and Zhihua Zhang. 2014. Distributed Power-law Graph Computing: Theoretical and Empirical Analysis. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems (NIPS). 1673\u20131681."},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696098"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.623"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614292"},{"key":"e_1_3_3_1_91_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona\u00a0T. Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. ArXiv Preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_3_1_92_2","first-page":"995","volume-title":"Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Zhang Zili","year":"2023","unstructured":"Zili Zhang, Chao Jin, Linpeng Tang, Xuanzhe Liu, and Xin Jin. 2023. Fast, Approximate Vector Queries on Very Large Unstructured Datasets. In Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI). 995\u20131011."},{"key":"e_1_3_3_1_93_2","first-page":"60626","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Zhang Zhihao","year":"2024","unstructured":"Zhihao Zhang, Alan Zhu, Lijie Yang, Yihua Xu, Lanting Li, Phitchaya\u00a0Mangpo Phothilimthana, and Zhihao Jia. 2024. Accelerating Iterative Retrieval-augmented Language Model Serving with Speculation. In Proceedings of the International Conference on Machine Learning (ICML). 60626\u201360643."},{"key":"e_1_3_3_1_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"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\/3695053.3731089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:06:18Z","timestamp":1750503978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":93,"alternative-id":["10.1145\/3695053.3731089","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731089","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"}}]}}