{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:55:30Z","timestamp":1782834930807,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","funder":[{"name":"SRC\/DARPA JUMP 2.0"},{"DOI":"10.13039\/100000899","name":"Intel Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000899","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MSIT IITP","award":["RS-2024-00456287"],"award-info":[{"award-number":["RS-2024-00456287"]}]},{"name":"NRF Korea","award":["RS-2024-00405857"],"award-info":[{"award-number":["RS-2024-00405857"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756102","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1809-1823","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Re-architecting End-host Networking with CXL: Coherence, Memory, and Offloading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8402-0127","authenticated-orcid":false,"given":"Houxiang","family":"Ji","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8389-2133","authenticated-orcid":false,"given":"Yifan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Meta, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7531-3365","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7513-2858","authenticated-orcid":false,"given":"Ipoom","family":"Jeong","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2937-5804","authenticated-orcid":false,"given":"Ren","family":"Wang","sequence":"additional","affiliation":[{"name":"Intel Corp., Portland, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1530-2568","authenticated-orcid":false,"given":"Saksham","family":"Agarwal","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5634","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926289"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358278"},{"key":"e_1_3_3_2_4_2","unstructured":"Altera. accessed in 2025. Agilex 7 R-Tile Compute Express Link 1.1\/2.0 FPGA IP User Guide."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422604.3425923"},{"key":"e_1_3_3_2_6_2","volume-title":"Proceedings of the 5th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201913)","author":"Blott Michaela","year":"2013","unstructured":"Michaela Blott, Kimon Karras, Ling Liu, Kees Vissers, Jeremia B\u00e4r, and Zsolt Istv\u00e1n. 2013. Achieving 10gbps Line-rate Key-Value Stores with FPGAs. In Proceedings of the 5th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud\u201913)."},{"key":"e_1_3_3_2_7_2","volume-title":"Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS\u201920)","author":"Choi Sean","year":"2020","unstructured":"Sean Choi, Muhammad Shahbaz, Balaji Prabhakar, and Mendel Rosenblum. 2020. \u03bb -NIC: Interactive Serverless Compute on Programmable SmartNICs. In Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS\u201920)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507742"},{"key":"e_1_3_3_2_9_2","unstructured":"Compute Express Link Consortium. accessed in 2025. Compute Express Link Specification Revision 3.1. https:\/\/computeexpresslink.org\/wp-content\/uploads\/2024\/02\/CXL-3.1-Specification.pdf."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750415"},{"key":"e_1_3_3_2_11_2","volume-title":"Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS\u201919)","author":"Daglis Alexandros","year":"2019","unstructured":"Alexandros Daglis, Mark Sutherland, and Babak Falsafi. 2019. RPCValet: NI-Driven Tail-Aware Balancing of \u03bc s-Scale RPCs. In Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS\u201919)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Debendra Das\u00a0Sharma Robert Blankenship and Daniel Berger. 2024. An Introduction to the Compute Express Link (CXL) Interconnect. ACM Comput. Surv. (2024).","DOI":"10.1145\/3669900"},{"key":"e_1_3_3_2_13_2","volume-title":"Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201918)","author":"Firestone Daniel","year":"2018","unstructured":"Daniel Firestone, Andrew Putnam, Sambhrama Mundkur, Derek Chiou, Alireza Dabagh, Mike Andrewartha, Hari Angepat, Vivek Bhanu, Adrian Caulfield, Eric Chung, Harish\u00a0Kumar Chandrappa, Somesh Chaturmohta, Matt Humphrey, Lavier Jack, Lam Norman, Fengfen Liu, Kalin Ovtcharov, Jitu Padhye, Gautham Popuri, Shachar Raindel, Tejas Sapre, Mark Shaw, Madhan Silva, Ganriel nd\u00a0Sivakumar, Nisheeth Srivastava, Anshuman Verma, Qasim Zuhair, Deepak Bansal, Doug Burger, Kushagra Vaid, Dvid\u00a0A. Maltz, and Albert Greenberg. 2018. Azure Accelerated Networking: SmartNICs in the Public Cloud. In Proceedings of the 15th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201918)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.5555\/2535461.2535502"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691843"},{"key":"e_1_3_3_2_16_2","volume-title":"Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201921)","author":"Ibanez Stephen","year":"2021","unstructured":"Stephen Ibanez, Alex Mallery, Serhat Arslan, Theo Jepsen, Muhammad Shahbaz, Changhoon Kim, and Nick McKeown. 2021. The nanoPU: A Aanosecond Network Stack for Datacenters. In Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201921)."},{"key":"e_1_3_3_2_17_2","unstructured":"Intel. accessed in 2025. Data Plane Development Kit (DPDK). https:\/\/www.dpdk.org."},{"key":"e_1_3_3_2_18_2","unstructured":"Intel Corporation. accessed in 2025. Agilex\u2122 7 FPGA I-Series Development Kit. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/fpga\/development-kits\/agilex\/agi027.html."},{"key":"e_1_3_3_2_19_2","unstructured":"Intel Corporation. accessed in 2025. Intel Xeon Processor Scalable Family Technical Overview. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/xeon-processor-scalable-family-technical-overview.html."},{"key":"e_1_3_3_2_20_2","unstructured":"Intel Corporation. accessed in 2025. Optimizing Computer Applications for Latency: Part 1: Configuring the Hardware. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/optimizing-computer-applications-for-latency-part-1-configuring-the-hardware.html."},{"key":"e_1_3_3_2_21_2","volume-title":"Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201914)","author":"Jeong EunYoung","year":"2014","unstructured":"EunYoung Jeong, Shinae Wood, Muhammad Jamshed, Haewon Jeong, Sunghwan Ihm, Dongsu Han, and KyoungSoo Park. 2014. mTCP: a Highly Scalable User-level TCP Stack for Multicore Systems. In Proceedings of the 11th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201914)."},{"key":"e_1_3_3_2_22_2","volume-title":"Proceedings of the 2023 USENIX Annual Technical Conference (ATC\u201923)","author":"Ji Houxiang","year":"2023","unstructured":"Houxiang Ji, Mark Mansi, Yan Sun, Yifan Yuan, Jinghan Huang, Reese Kuper, Michael\u00a0M. Swift, and Nam\u00a0Sung Kim. 2023. STYX: Exploiting SmartNIC Capability to Reduce Datacenter Memory Tax. In Proceedings of the 2023 USENIX Annual Technical Conference (ATC\u201923)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00110"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132764"},{"key":"e_1_3_3_2_25_2","volume-title":"Proceedings of the 2016 USENIX annual technical conference (ATC\u201916)","author":"Kalia Anuj","year":"2016","unstructured":"Anuj Kalia, Michael Kaminsky, and David\u00a0G Andersen. 2016. Design Guidelines for High Performance RDMA Systems. In Proceedings of the 2016 USENIX annual technical conference (ATC\u201916)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483565"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446696"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3132252"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483561"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132756"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600061.3600063"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132751"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485926"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2015.43"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715987"},{"key":"e_1_3_3_2_37_2","volume-title":"Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201920)","author":"Moon YoungGyoun","year":"2020","unstructured":"YoungGyoun Moon, SeungEon Lee, Muhammad\u00a0Asim Jamshed, and KyoungSoo Park. 2020. AccelTCP: Accelerating Network Applications with Stateful TCP Offloading. In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201920)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230560"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541965"},{"key":"e_1_3_3_2_40_2","unstructured":"NVIDIA Corporation. accessed in 2025. DOCA Documentation. https:\/\/docs.nvidia.com\/doca\/sdk\/doca+dma\/index.html."},{"key":"e_1_3_3_2_41_2","unstructured":"NVIDIA Corporation. accessed in 2025. NVIDIA BlueField-3 DPU. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/Data-Center\/documents\/datasheet-nvidia-bluefield-3-dpu.pdf."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507711"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480055"},{"key":"e_1_3_3_2_44_2","volume-title":"Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201923)","author":"Sadok Hugo","year":"2023","unstructured":"Hugo Sadok, Nirav Atre, Zhipeng Zhao, Daniel\u00a0S. Berger, James\u00a0C. Hoe, Aurojit Panda, Justine Sherry, and Ren Wang. 2023. Enso: A Streaming Interface for NIC-Application Communication. In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201923)."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Khaled Salah. 2007. To Coalesce or Not To Coalesce. AEU-International Journal of Electronics and Communications 61 4 (2007) 215\u2013225.","DOI":"10.1016\/j.aeue.2006.04.007"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152461"},{"key":"e_1_3_3_2_47_2","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI\u201921)","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan 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\u201921)."},{"key":"e_1_3_3_2_48_2","unstructured":"Anirudh Sarma Hamed Seyedroudbari Harshit Gupta Umakishore Ramachandran and Alexandros Daglis. 2022. Nfslicer: Data Movement Optimization for Shallow Network Functions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.02585 (2022)."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624868"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483555"},{"key":"e_1_3_3_2_51_2","volume-title":"Proceedings of the 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA\u201923)","author":"Seyedroudbari Hamed","year":"2023","unstructured":"Hamed Seyedroudbari, Srikar Vanavasam, and Alexandros Daglis. 2023. Turbo: SmartNIC-enabled Dynamic Load Balancing of \u03bc s-scale RPCs. In Proceedings of the 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA\u201923)."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387519"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Samuel\u00a0W Stark A\u00a0Theodore Markettos and Simon\u00a0W Moore. 2023. How Flexible is CXL\u2019s Memory Protection? Replacing a sledgehammer with a scalpel. Queue (2023).","DOI":"10.1145\/3606014"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3711999"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614256"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00027"},{"key":"e_1_3_3_2_57_2","volume-title":"Proceedings of the 23rd USENIX security symposium (USENIX security 14)","author":"Varadarajan Venkatanathan","year":"2014","unstructured":"Venkatanathan Varadarajan, Thomas Ristenpart, and Michael Swift. 2014. Scheduler-based defenses against { Cross-VM} side-channels. In Proceedings of the 23rd USENIX security symposium (USENIX security 14)."},{"key":"e_1_3_3_2_58_2","volume-title":"Proceedings of the 19th USENIX Conference on File and Storage Technologies (FAST\u201921)","author":"Wang Qing","year":"2021","unstructured":"Qing Wang, Youyou Lu, Erci Xu, Junru Li, Youmin Chen, and Jiwu Shu. 2021. Concordia: Distributed Shared Memory with In-Network Cache Coherence. In Proceedings of the 19th USENIX Conference on File and Storage Technologies (FAST\u201921)."},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707239"},{"key":"e_1_3_3_2_60_2","volume-title":"Proceedings of the 23rd USENIX security symposium (USENIX security\u201914)","author":"Yarom Yuval","year":"2014","unstructured":"Yuval Yarom and Katrina Falkner. 2014. { FLUSH+ RELOAD} : A high resolution, low noise, l3 cache { Side-Channel} attack. In Proceedings of the 23rd USENIX security symposium (USENIX security\u201914)."},{"key":"e_1_3_3_2_61_2","volume-title":"Proceedings of the 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA\u201921)","author":"Yuan Yifan","year":"2021","unstructured":"Yifan Yuan, Mohammad Alian, Yipeng Wang, Ren Wang, Ilia Kurakin, Charlie Tai, and Nam\u00a0Sung Kim. 2021. Don\u2019t Forget the I\/O When Allocating Your LLC. In Proceedings of the 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA\u201921)."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071127"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707285"},{"key":"e_1_3_3_2_64_2","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201924)","author":"Zhong Yuhong","year":"2024","unstructured":"Yuhong Zhong, Daniel\u00a0S Berger, Carl Waldspurger, Ryan Wee, Ishwar Agarwal, Rajat Agarwal, Frank Hady, Karthik Kumar, Mark\u00a0D Hill, Mosharaf Chowdhury, et\u00a0al. 2024. Managing Memory Tiers with CXL in Virtualized Environments. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201924)."},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978324"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:43:28Z","timestamp":1769463808000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":64,"alternative-id":["10.1145\/3725843.3756102","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756102","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}