{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:28:18Z","timestamp":1786476498048,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,17]]},"DOI":"10.1145\/3789240.3822571","type":"proceedings-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:33:22Z","timestamp":1786473202000},"page":"2102-2108","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Monoliths: Enabling Flexible and Composable AI Systems via Memory Disaggregation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2831-6643","authenticated-orcid":false,"given":"Divya Kiran","family":"Kadiyala","sequence":"first","affiliation":[{"name":"Future Technologies (SIAD), Hewlett Packard Enterprise, Milpitas, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3408-9050","authenticated-orcid":false,"given":"Lianjie","family":"Cao","sequence":"additional","affiliation":[{"name":"Networking and Distributed Systems Lab (NDSL), Hewlett Packard Enterprise Labs, Milpitas, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0487-1693","authenticated-orcid":false,"given":"Jinsun","family":"Yoo","sequence":"additional","affiliation":[{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"},{"name":"Networking and Distributed Systems Lab (NDSL), Hewlett Packard Enterprise Labs, Milpitas, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4594-8164","authenticated-orcid":false,"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[{"name":"Networking and Distributed Systems Lab (NDSL), Hewlett Packard Enterprise Labs, Milpitas, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2564-4852","authenticated-orcid":false,"given":"Samantika","family":"Sury","sequence":"additional","affiliation":[{"name":"Future Technologies (SIAD), Hewlett Packard Enterprise, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0211-1666","authenticated-orcid":false,"given":"Alexandros","family":"Daglis","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh, Scotland, United Kingdom"},{"name":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446089"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3606557.3606563"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545054"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.14315"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446713"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00101"},{"key":"e_1_3_2_1_7_1","unstructured":"UALink Consortium. [n. d.]. Ultra Accelerator Link. Accessed on April 27 2026 ([n. d.]). https:\/\/ualinkconsortium.org\/"},{"key":"e_1_3_2_1_8_1","unstructured":"Broadcomm Corporation. [n. d.]. Scale Up Ethernet. Accessed on April 27 2026 ([n. d.]). https:\/\/www.opencompute.org\/documents\/ocp-sue-spec-final-pdf-1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.12948"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3250407"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3545924"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.11805"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.IOT.2022.100514"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3655038.3665953"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 2022 USENIX Annual Technical Conference, USENIX ATC 2022","author":"Gouk Donghyun","year":"2022","unstructured":"Donghyun Gouk, Sangwon Lee, Miryeong Kwon, and Myoungsoo Jung. 2022. Direct Access, High-Performance Memory Disaggregation with DirectCXL. In Proceedings of the 2022 USENIX Annual Technical Conference, USENIX ATC 2022, Carlsbad, CA, USA, July 11-13, 2022, Jiri Schindler and Noa Zilberman (Eds.). USENIX Association, 287\u2013294. https:\/\/www.usenix.org\/conference\/atc22\/presentation\/gouk"},{"key":"e_1_3_2_1_16_1","volume-title":"Efficient Memory Disaggregation with Infiniswap. In 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017","author":"Gu Juncheng","year":"2017","unstructured":"Juncheng Gu, Youngmoon Lee, Yiwen Zhang, Mosharaf Chowdhury, and Kang G. Shin. 2017. Efficient Memory Disaggregation with Infiniswap. In 14th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2017, Boston, MA, USA, March 27-29, 2017, Aditya Akella and Jon Howell (Eds.). USENIX Association, 649\u2013667. https:\/\/www.usenix.org\/conference\/nsdi17\/technical-sessions\/presentation\/gu"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2510.04871"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00096"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2012.6168955"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555789"},{"key":"e_1_3_2_1_23_1","unstructured":"LIQID. [n. d.]. LIQID Composable Memory Solutions. Accessed on April 24 2026 ([n. d.]). https:\/\/www.liqid.com\/products\/composable-memory-solutions"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00165"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2209249.2209269"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3606557.3606562"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589985"},{"key":"e_1_3_2_1_28_1","volume-title":"The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. (April 5","author":"April","year":"2025","unstructured":"Meta. April 5, 2025. The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. (April 5, 2025). https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/SUM60964.2024.10614558"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00055"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190537"},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA. [n. d.]. NVIDIA GB200 NVL72. Accessed on July 7 2025 ([n. d.]). https:\/\/www.nvidia.com\/en-us\/data-center\/gb200-nvl72\/"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2601.03267"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00049"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC363308.2025.10956516"},{"key":"e_1_3_2_1_36_1","volume-title":"Scaling Distributed Machine Learning with In-Network Aggregation. In 18th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2021","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan R. K. Ports, and Peter Richt\u00e1rik. 2021. Scaling Distributed Machine Learning with In-Network Aggregation. In 18th USENIX Symposium on Networked Systems Design and Implementation, NSDI 2021, April 12-14, 2021, James Mickens and Renata Teixeira (Eds.). USENIX Association, 785\u2013808. https:\/\/www.usenix.org\/conference\/nsdi21\/presentation\/sapio"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI55740.2022.00017"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3235972"},{"key":"e_1_3_2_1_39_1","volume-title":"Accessed","author":"Shilov Anton","year":"2024","unstructured":"Anton Shilov. May 14, 2024. Nvidia's next-gen Blackwell AI Super-chips could cost up to $70,000 fullyequipped server racks reportedly range up to $3,000,000 or more. Accessed: June 2025 (May 14, 2024). https:\/\/www.tomshardware.com\/pc-components\/gpus\/nvidias-next-gen-blackwell-ai-gpus-to-cost-up-to-dollar70000-fully-equipped-servers-range-up-to-dollar3000000-report"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690639"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00053"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701296"},{"key":"e_1_3_2_1_43_1","volume-title":"d.]. UEC 1.0: NEW HIGH-PERFORMANCE STANDARD FOR SCALING HPC-AI","author":"Ultra Ethernet Consortium","year":"2025","unstructured":"Ultra Ethernet Consortium. [n. d.]. UEC 1.0: NEW HIGH-PERFORMANCE STANDARD FOR SCALING HPC-AI. Accessed: July 2025 ([n. d.]). https:\/\/ultraethernet.org\/wp-content\/uploads\/sites\/20\/2025\/06\/UEC1.0Whitepaper.pdf"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3561261.3561263"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00100"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567488"},{"key":"e_1_3_2_1_47_1","volume-title":"Anurag Khandelwal, and Lin Zhong.","author":"Yu Yanpeng","year":"2023","unstructured":"Yanpeng Yu, Seung seob Lee, Anurag Khandelwal, and Lin Zhong. 2023. GCS: Generalized Cache Coherence For Efficient Synchronization. arXiv:2301.02576 [cs.DC] https:\/\/arxiv.org\/abs\/2301.02576"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.09148"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467877"},{"key":"e_1_3_2_1_50_1","unstructured":"Pengfei Zuo Huimin Lin Junbo Deng Nan Zou Xingkun Yang Yingyu Diao Weifeng Gao Ke Xu Zhangyu Chen Shirui Lu Zhao Qiu Peiyang Li Xianyu Chang Zhengzhong Yu Fangzheng Miao Jia Zheng Ying Li Yuan Feng Bei Wang Zaijian Zong Mosong Zhou Wenli Zhou Houjiang Chen Xingyu Liao Yipeng Li Wenxiao Zhang Ping Zhu Yinggang Wang Chuanjie Xiao Depeng Liang Dong Cao Juncheng Liu Yongqiang Yang Xiaolong Bai Yi Li Huaguo Xie Huatao Wu Zhibin Yu Lv Chen Hu Liu Yujun Ding Haipei Zhu Jing Xia Yi Xiong Zhou Yu and Heng Liao. 2025. Serving Large Language Models on Huawei CloudMatrix384. arXiv:2506.12708 [cs.DC] https:\/\/arxiv.org\/abs\/2506.12708"}],"event":{"name":"SIGCOMM '26: ACM SIGCOMM 2026 Conference","location":"Colorado Convention Center Denver CO USA","acronym":"SIGCOMM '26","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2026 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3789240.3822571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T18:47:59Z","timestamp":1786474079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3789240.3822571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":50,"alternative-id":["10.1145\/3789240.3822571","10.1145\/3789240"],"URL":"https:\/\/doi.org\/10.1145\/3789240.3822571","relation":{},"subject":[],"published":{"date-parts":[[2026,8,11]]},"assertion":[{"value":"2026-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}