{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:18:54Z","timestamp":1774455534543,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731016","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"631-645","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Cramming a Data Center into One Cabinet, a Co-Exploration of Computing and Hardware Architecture of Waferscale Chip"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0275-5670","authenticated-orcid":false,"given":"Xingmao","family":"Yu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4379-694X","authenticated-orcid":false,"given":"Dingcheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8666-8463","authenticated-orcid":false,"given":"Jinyi","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6009-4232","authenticated-orcid":false,"given":"Jingyao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6218-4659","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"SJTU, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8438-8588","authenticated-orcid":false,"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-4395","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Amey Agrawal Ashish Panwar Jayashree Mohan Nipun Kwatra Bhargav\u00a0S Gulavani and Ramachandran Ramjee. 2023. Sarathi: Efficient llm inference by piggybacking decodes with chunked prefills. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.16369 (2023)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01761-2"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567066"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00022"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895625"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00025"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Sumin Choi Heegon Kim Daniel\u00a0H Jung Jonghoon\u00a0Jay Kim Jaemin Lim and Joungho Kim. 2016. An efficient crosstalk-included eye-diagram estimation method for high-speed interposer channel on 2.5-D and 3-D IC. IEEE Transactions on Electromagnetic Compatibility 59 3 (2016) 927\u2013939.","DOI":"10.1109\/TEMC.2016.2630080"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Jack Choquette. 2023. NVIDIA Hopper H100 GPU: Scaling Performance. IEEE Micro 43 3 (2023) 9\u201317. 10.1109\/MM.2023.3256796","DOI":"10.1109\/MM.2023.3256796"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC32862.2020.00013"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530428"},{"key":"e_1_3_3_1_12_2","unstructured":"Yinhe Han Haobo Xu Meixuan Lu Haoran Wang Junpei Huang Ying Wang Yujie Wang Feng Min Qi Liu Ming Liu et\u00a0al. 2023. The Big Chip: Challenge Model and Architecture. Fundamental Research (2023)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Yang Hu Xinhan Lin Huizheng Wang Zhen He Xingmao Yu Jiahao Zhang Qize Yang Zheng Xu Sihan Guan Jiahao Fang et\u00a0al. 2024. Wafer-Scale Computing: Advancements Challenges and Future Perspectives [Feature]. IEEE Circuits and Systems Magazine 24 1 (2024) 52\u201381.","DOI":"10.1109\/MCAS.2024.3349669"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC32696.2021.00028"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062984"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/EDAPS56906.2022.9995183"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Kiyeong Kim Chulsoon Hwang Kyoungchoul Koo Jonghyun Cho Heegon Kim Joungho Kim Junho Lee Hyung-Dong Lee Kun-Woo Park and Jun\u00a0So Pak. 2012. Modeling and analysis of a power distribution network in TSV-based 3-D memory IC including P\/G TSVs on-chip decoupling capacitors and silicon substrate effects. IEEE Transactions on Components Packaging and Manufacturing Technology 2 12 (2012) 2057\u20132070.","DOI":"10.1109\/TCPMT.2012.2214482"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Kiyeong Kim Jong\u00a0Min Yook Junchul Kim Heegon Kim Junho Lee Kunwoo Park and Joungho Kim. 2013. Interposer power distribution network (PDN) modeling using a segmentation method for 3-D ICs with TSVs. IEEE Transactions on Components Packaging and Manufacturing Technology 3 11 (2013) 1891\u20131906.","DOI":"10.1109\/TCPMT.2013.2276050"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Seongguk Kim Subin Kim Kyungjun Cho Taein Shin Hyunwook Park Daehwan Lho Shinyoung Park Kyungjune Son Gapyeol Park Seungtaek Jeong et\u00a0al. 2021. Signal integrity and computing performance analysis of a processing-in-memory of high bandwidth memory (PIM-HBM) scheme. IEEE Transactions on Components Packaging and Manufacturing Technology 11 11 (2021) 1955\u20131970.","DOI":"10.1109\/TCPMT.2021.3117071"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Seongguk Kim Subin Kim Kyungjun Cho Taein Shin Hyunwook Park Daehwan Lho Shinyoung Park Kyungjune Son Gapyeol Park Seungtaek Jeong et\u00a0al. 2021. Signal integrity and computing performance analysis of a processing-in-memory of high bandwidth memory (PIM-HBM) scheme. IEEE Transactions on Components Packaging and Manufacturing Technology 11 11 (2021) 1955\u20131970.","DOI":"10.1109\/TCPMT.2021.3117071"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"N Kumar K Kennedy K Gildersleeve R Abelson CM Mastrangelo and DC Montgomery. 2006. A review of yield modelling techniques for semiconductor manufacturing. International Journal of Production Research 44 23 (2006) 5019\u20135036.","DOI":"10.1080\/00207540600596874"},{"key":"e_1_3_3_1_22_2","unstructured":"Sameer Kumar and Norm Jouppi. 2020. Highly available data parallel ml training on mesh networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2011.03605 (2020)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Gary Lauterbach. 2021. The path to successful wafer-scale integration: The cerebras story. IEEE Micro 41 6 (2021) 52\u201357.","DOI":"10.1109\/MM.2021.3112025"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnology18217.2020.9265085"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Ang Li Shuaiwen\u00a0Leon Song Jieyang Chen Jiajia Li Xu Liu Nathan\u00a0R. Tallent and Kevin\u00a0J. Barker. 2020. Evaluating Modern GPU Interconnect: PCIe NVLink NV-SLI NVSwitch and GPUDirect. IEEE Transactions on Parallel and Distributed Systems 31 1 (2020) 94\u2013110. 10.1109\/TPDS.2019.2928289","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"},{"key":"e_1_3_3_1_27_2","volume-title":"Hot Chips","author":"Lie Sean","year":"2019","unstructured":"Sean Lie. 2019. Wafer scale deep learning. In Hot Chips, Vol.\u00a031. Stanford Univ."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895479"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895479"},{"key":"e_1_3_3_1_30_2","unstructured":"Sean Lie. 2024. Wafer-Scale AI: GPU Impossible Performance. https:\/\/hc2024.hotchips.org\/assets\/program\/conference\/day2\/72_HC2024.Cerebras.Sean.v03.final.pdf Conference presentation; Accessed: [2025-04-30]."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10664673"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Ikuo Magaki Moein Khazraee Luis\u00a0Vega Gutierrez and Michael\u00a0Bedford Taylor. 2016. Asic clouds: Specializing the datacenter. ACM SIGARCH Computer Architecture News 44 3 (2016) 178\u2013190.","DOI":"10.1145\/3007787.3001156"},{"key":"e_1_3_3_1_33_2","volume-title":"Llama 2 Chat (70B)","author":"Team Meta AI Research","year":"2023","unstructured":"Meta AI Research Team. 2023. Llama 2 Chat (70B). Accessed: 2025-02-22, Licensed under LLAMA 2 Community License."},{"key":"e_1_3_3_1_34_2","first-page":"11","volume-title":"Electron devices meeting","author":"Moore Gordon\u00a0E","year":"1975","unstructured":"Gordon\u00a0E Moore et\u00a0al. 1975. Progress in digital integrated electronics. In Electron devices meeting, Vol.\u00a021. Washington, DC, 11\u201313."},{"key":"e_1_3_3_1_35_2","unstructured":"Elon Musk. 2021. Tesla AI Day \u2013 The Presentation (I). https:\/\/elon-musk-interviews.com\/2021\/08\/31\/tesla-ai-day-the-presentation-i\/ Accessed: 2025-02-21."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00014"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586194"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00042"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_1_40_2","unstructured":"SemiWiki. 2025. TSMC Brings Packaging Center Stage with Silicon. SemiWiki Article. https:\/\/semiwiki.com\/events\/355074-tsmc-brings-packaging-center-stage-with-silicon\/ Accessed: [2025-04-30]."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Debendra\u00a0Das Sharma. 2020. PCI Express 6.0 specification: A low-latency high-bandwidth high-reliability and cost-effective interconnect with 64.0 GT\/s PAM-4 signaling. IEEE Micro 41 1 (2020) 23\u201329.","DOI":"10.1109\/MM.2020.3039925"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Debendra\u00a0Das Sharma Gerald Pasdast Zhiguo Qian and Kemal Aygun. 2022. Universal chiplet interconnect express (UCIe): An open industry standard for innovations with chiplets at package level. IEEE Transactions on Components Packaging and Manufacturing Technology 12 9 (2022) 1423\u20131431.","DOI":"10.1109\/TCPMT.2022.3207195"},{"key":"e_1_3_3_1_43_2","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick Legresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.08053 (March 2020). https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-07312-0_2"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2980095"},{"key":"e_1_3_3_1_46_2","unstructured":"Cerebras Systems. 2022. Cerebras Wafer-Scale Cluster Brings Push-Button Ease and Linear Performance Scaling to Large Language Models. Cerebras Systems Press Release. Accessed: 2025-04-29."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895534"},{"key":"e_1_3_3_1_49_2","unstructured":"Meta AI\u00a0Research Team. 2023. Llama 2 Chat (7B). https:\/\/huggingface.co\/meta-llama\/Llama-2-7b-chat-hf. Accessed: 2025-02-22 Licensed under the LLAMA 2 Community License."},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"crossref","unstructured":"Ming-Yi Tsai and Yu-Wen Wang. 2019. A theoretical solution for thermal warpage of flip-chip packages. IEEE Transactions on Components Packaging and Manufacturing Technology 10 1 (2019) 72\u201378.","DOI":"10.1109\/TCPMT.2019.2933546"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"crossref","unstructured":"Shaoxi Wang Yue Yin Chenxia Hu and Pouya Rezai. 2018. 3D integrated circuit cooling with microfluidics. Micromachines 9 6 (2018) 287.","DOI":"10.3390\/mi9060287"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00035"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"Li Zheng Yang Zhang and Muhannad\u00a0S. Bakir. 2015. A Silicon Interposer Platform Utilizing Microfluidic Cooling for High-Performance Computing Systems. IEEE Transactions on Components Packaging and Manufacturing Technology 5 10 (2015) 1379\u20131386. 10.1109\/TCPMT.2015.2470544","DOI":"10.1109\/TCPMT.2015.2470544"},{"key":"e_1_3_3_1_54_2","first-page":"193","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang. 2024. { DistServe} : Disaggregating prefill and decoding for goodput-optimized large language model serving. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 193\u2013210."},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","unstructured":"Minghao Zhou Li Li Fengze Hou Guoqiang He and Jiaqi Fan. 2022. Thermal Modeling of a Chiplet-Based Packaging With a 2.5-D Through-Silicon Via Interposer. IEEE Transactions on Components Packaging and Manufacturing Technology 12 6 (2022) 956\u2013963. 10.1109\/TCPMT.2022.3174608","DOI":"10.1109\/TCPMT.2022.3174608"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549404"}],"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\/3695053.3731016","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:02:52Z","timestamp":1750503772000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731016"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":55,"alternative-id":["10.1145\/3695053.3731016","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731016","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"}}]}}