{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:03:49Z","timestamp":1782950629654,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSFC","award":["62032013"],"award-info":[{"award-number":["62032013"]}]},{"name":"NSFC","award":["62272258"],"award-info":[{"award-number":["62272258"]}]},{"name":"NSFC","award":["62372053"],"award-info":[{"award-number":["62372053"]}]},{"name":"NSFC-RGC","award":["62061160489"],"award-info":[{"award-number":["62061160489"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,4]]},"DOI":"10.1145\/3651890.3672214","type":"proceedings-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T13:11:43Z","timestamp":1722431503000},"page":"904-920","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["OptimusPrime: Unleash Dataplane Programmability through a Transformable Architecture"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2568-6184","authenticated-orcid":false,"given":"Zhikang","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9662-3449","authenticated-orcid":false,"given":"Yong","family":"Feng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2227-510X","authenticated-orcid":false,"given":"Shuxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5377-6628","authenticated-orcid":false,"given":"Haoyu","family":"Song","sequence":"additional","affiliation":[{"name":"Futurewei Technologies, Santa Clara, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9256-370X","authenticated-orcid":false,"given":"Hanyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0277-1495","authenticated-orcid":false,"given":"Tong","family":"Yun","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1918-6832","authenticated-orcid":false,"given":"Wenquan","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7718-0669","authenticated-orcid":false,"given":"Tian","family":"Pan","sequence":"additional","affiliation":[{"name":"Purple Mountain Laboratories, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8588-8744","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. 2023. AMD Pensando. https:\/\/www.amd.com\/en\/accelerators\/pensando."},{"key":"e_1_3_2_1_2_1","volume-title":"Disaggregating Stateful Network Functions. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Bansal Deepak","year":"2023","unstructured":"Deepak Bansal, Gerald DeGrace, Rishabh Tewari, Michal Zygmunt, James Grantham, Silvano Gai, Mario Baldi, Krishna Doddapaneni, Arun Selvarajan, Arunkumar Arumugam, Balakrishnan Raman, Avijit Gupta, Sachin Jain, Deven Jagasia, Evan Langlais, Pranjal Srivastava, Rishiraj Hazarika, Neeraj Motwani, Soumya Tiwari, Stewart Grant, Ranveer Chandra, and Srikanth Kandula. 2023. Disaggregating Stateful Network Functions. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1469--1487."},{"key":"e_1_3_2_1_3_1","volume-title":"17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20)","author":"Barbette Tom","year":"2020","unstructured":"Tom Barbette, Chen Tang, Haoran Yao, Dejan Kosti\u0107, Gerald Q Maguire Jr, Panagiotis Papadimitratos, and Marco Chiesa. 2020. A High-Speed Load-Balancer Design with Guaranteed Per-Connection-Consistency. In 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI 20). 667--683."},{"key":"e_1_3_2_1_4_1","volume-title":"On a routing problem. Quarterly of applied mathematics 16, 1","author":"Bellman Richard","year":"1958","unstructured":"Richard Bellman. 1958. On a routing problem. Quarterly of applied mathematics 16, 1 (1958), 87--90."},{"key":"e_1_3_2_1_5_1","volume-title":"Efficient Measurement on Programmable Switches Using Probabilistic Recirculation. In 2018 IEEE 26th International Conference on Network Protocols (ICNP). IEEE, 313--323","author":"Ben-Basat Ran","year":"2018","unstructured":"Ran Ben-Basat, Xiaoqi Chen, Gil Einziger, and Ori Rottenstreich. 2018. Efficient Measurement on Programmable Switches Using Probabilistic Recirculation. In 2018 IEEE 26th International Conference on Network Protocols (ICNP). IEEE, 313--323."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2656877.2656890"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486011"},{"key":"e_1_3_2_1_8_1","unstructured":"Broadcom. 2023. Broadcom Trident 4. https:\/\/www.broadcom.com\/products\/ethernet-connectivity\/switching\/strataxgs\/bcm56880-series."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098823"},{"key":"e_1_3_2_1_10_1","unstructured":"Cisco. 2023. Cisco Silicon One. https:\/\/www.cisco.com\/c\/en\/us\/solutions\/silicon-one.html."},{"key":"e_1_3_2_1_11_1","volume-title":"Operating systems theory","author":"Coffman Edward Grady","unstructured":"Edward Grady Coffman and Peter J Denning. 1973. Operating systems theory. Vol. 973. prentice-Hall Englewood Cliffs, NJ."},{"key":"e_1_3_2_1_12_1","unstructured":"Intel Corporation. 2023. Intel Ethernet Switch FM6000 Series. https:\/\/www.intel.com\/content\/www\/us\/en\/collections\/products\/ethernet\/multi-host-controllers\/fm6000-controllers.html."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405879"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/191843.191886"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737832"},{"key":"e_1_3_2_1_16_1","unstructured":"Intel. 2023. Intel IPU. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/network-io\/ipu.html."},{"key":"e_1_3_2_1_17_1","unstructured":"Intel. 2023. Intel Tofino. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/details\/network-io\/intelligent-fabric-processors\/tofino-2.html."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123942"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132764"},{"key":"e_1_3_2_1_20_1","volume-title":"MIPS RISC architectures","author":"Kane Gerry","unstructured":"Gerry Kane and Joe Heinrich. 1992. MIPS RISC architectures. Prentice-Hall, Inc."},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"In-band network telemetry via programmable dataplanes","volume":"15","author":"Kim Changhoon","year":"2015","unstructured":"Changhoon Kim, Anirudh Sivaraman, Naga Praveen Kumar Katta, Antonin Bas, Advait Abhay Dixit, and Lawrence J Wobker. 2015. In-band network telemetry via programmable dataplanes. In ACM SIGCOMM, Vol. 15. 1--2.","journal-title":"ACM SIGCOMM"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405855"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373360.3380843"},{"key":"e_1_3_2_1_24_1","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael Swift. 2021. ATP: In-network aggregation for multi-tenant learning. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21). 741--761."},{"key":"e_1_3_2_1_25_1","volume-title":"Quantization-Aware In-Network Aggregation for Minimizing Communication Overhead. In Companion of the 19th International Conference on emerging Networking EXperiments and Technologies (CoNEXT","author":"Lee Hochan","year":"2023","unstructured":"Hochan Lee, Heewon Kim, Chanbin Bae, Yujin Kim, and Sangheon Pack. 2023. Quantization-Aware In-Network Aggregation for Minimizing Communication Overhead. In Companion of the 19th International Conference on emerging Networking EXperiments and Technologies (CoNEXT 2023). 57--58."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 18th European Conference on Computer Systems (EuroSys '23)","author":"Li Zhaoyi","year":"2023","unstructured":"Zhaoyi Li, Jiawei Huang, Yijun Li, Aikun Xu, Shengwen Zhou, Jingling Liu, and Jianxin Wang. 2023. A2TP: Aggregator-aware In-network Aggregation for Multitenant Learning. In Proceedings of the 18th European Conference on Computer Systems (EuroSys '23). 639--653."},{"key":"e_1_3_2_1_27_1","volume-title":"PANIC: A High-Performance Programmable NIC for Multi-tenant Networks. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Lin Jiaxin","year":"2020","unstructured":"Jiaxin Lin, Kiran Patel, Brent E Stephens, Anirudh Sivaraman, and Aditya Akella. 2020. PANIC: A High-Performance Programmable NIC for Multi-tenant Networks. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 243--259."},{"key":"e_1_3_2_1_28_1","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Liu Zaoxing","year":"2021","unstructured":"Zaoxing Liu, Hun Namkung, Georgios Nikolaidis, Jeongkeun Lee, Changhoon Kim, Xin Jin, Vladimir Braverman, Minlan Yu, and Vyas Sekar. 2021. Jaqen: A High-PerformanceSwitch-Native approach for detecting and mitigating volumetric DDoS attacks with programmable switches. In 30th USENIX Security Symposium (USENIX Security 21). 3829--3846."},{"key":"e_1_3_2_1_29_1","volume-title":"IEEE 21st International Conference on High Performance Switching and Routing (HPSR 20)","author":"Luinaud Thomas","unstructured":"Thomas Luinaud, Thibaut Stimpfling, Jeferson Santiago da Silva, Yvon Savaria, and J.M. Pierre Langlois. 2020. Bridging the Gap: FPGAs as Programmable Switches. In IEEE 21st International Conference on High Performance Switching and Routing (HPSR 20). 1--7."},{"key":"e_1_3_2_1_30_1","unstructured":"MARVELL. 2023. Marvell LiquidIO III An Inline DPU based SmartNIC for cloud network and security accesleration. https:\/\/www.marvell.com\/content\/dam\/marvell\/en\/public-collateral\/embedded-processors\/marvell-liquidio-III-solutions-brief.pdf."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098824"},{"key":"e_1_3_2_1_32_1","unstructured":"NPL. 2023. NPL. https:\/\/nplang.org\/."},{"key":"e_1_3_2_1_33_1","unstructured":"NVIDIA. 2023. NVIDIA BlueField Networking Platform. https:\/\/www.nvidia.com\/en-us\/networking\/products\/data-processing-unit\/."},{"key":"e_1_3_2_1_34_1","unstructured":"NVIDIA. 2023. NVIDIA DGX SuperPOD. https:\/\/docs.nvidia.com\/https:\/docs.nvidia.com\/dgx-superpod-reference-architecture-dgx-h100.pdf."},{"key":"e_1_3_2_1_35_1","unstructured":"NVIDIA. 2023. NVIDIA Spectrum. https:\/\/www.nvidia.com\/en-us\/networking\/products\/ethernet\/."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/170036.170081"},{"key":"e_1_3_2_1_37_1","volume-title":"FlowBlaze: Stateful Packet Processing in Hardware. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19)","author":"Pontarelli Salvatore","year":"2019","unstructured":"Salvatore Pontarelli, Roberto Bifulco, Marco Bonola, Carmelo Cascone, Marco Spaziani, Valerio Bruschi, Davide Sanvito, Giuseppe Siracusano, Antonio Capone, Michio Honda, Felipe Huici, and Giuseppe Bianchi. 2019. FlowBlaze: Stateful Packet Processing in Hardware. In 16th USENIX Symposium on Networked Systems Design and Implementation (NSDI 19). 531--548."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273440.1250709"},{"key":"e_1_3_2_1_39_1","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Scazzariello Mariano","year":"2023","unstructured":"Mariano Scazzariello, Tommaso Caiazzi, Hamid Ghasemirahni, Tom Barbette, Dejan Kosti\u0107, and Marco Chiesa. 2023. A High-Speed Stateful Packet Processing Approach for Tbps Programmable Switches. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 1237--1255."},{"key":"e_1_3_2_1_40_1","unstructured":"David Seal. 2001. ARM architecture reference manual. Pearson Education."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544269"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934900"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3050220.3063772"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472903"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067333"},{"key":"e_1_3_2_1_46_1","unstructured":"SYNOPSYS. 2023. Synopsys Design Compiler. https:\/\/www.synopsys.com\/implementation-and-signoff\/rtl-synthesis-test\/dc-ultra.html."},{"key":"e_1_3_2_1_47_1","unstructured":"UEC. 2023. Ultra Ethernet Consortium. https:\/\/ultraethernet.org\/."},{"key":"e_1_3_2_1_48_1","unstructured":"NC State University. 2023. NCSU FreePDK45. https:\/\/eda.ncsu.edu\/freepdk\/freepdk45\/."},{"key":"e_1_3_2_1_49_1","unstructured":"Weiyang Wang Manya Ghobadi Kayvon Shakeri Ying Zhang and Naader Hasani. 2023. How to Build Low-cost Networks for Large Language Models (without Sacrificing Performance)? arXiv:2307.12169"},{"key":"e_1_3_2_1_50_1","unstructured":"Andrew Waterman and Krste Asanovi\u0107. 2019. The RISC-V Instruction Set Manual Volume I: User-Level ISA Document Version 20190608-Base-Ratified. https:\/\/riscv.org\/wp-content\/uploads\/2019\/06\/riscv-spec.pdf."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3365609.3365849"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604835"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"},{"key":"e_1_3_2_1_54_1","volume-title":"19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22)","author":"Zeng Chaoliang","year":"2022","unstructured":"Chaoliang Zeng, Layong Luo, Teng Zhang, Zilong Wang, Luyang Li, Wenchen Han, Nan Chen, Lebing Wan, Lichao Liu, Zhipeng Ding, Xiongfei Geng, Tao Feng, Feng Ning, Kai Chen, and Chuanxiong Guo. 2022. Tiara: A Scalable and Efficient Hardware Acceleration Architecture for Stateful Layer-4 Load Balancing. In 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI 22). 1345--1358."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.24007"},{"key":"e_1_3_2_1_56_1","volume-title":"XAgg: Accelerating Heterogeneous Distributed Training Through XDP-Based Gradient Aggregation","author":"Zhang Qianyu","year":"2023","unstructured":"Qianyu Zhang, Gongming Zhao, Hongli Xu, and Peng Yang. 2023. XAgg: Accelerating Heterogeneous Distributed Training Through XDP-Based Gradient Aggregation. IEEE\/ACM Transactions on Networking (2023), 1--15."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604813"},{"key":"e_1_3_2_1_58_1","volume-title":"In-Network Machine Learning Using Programmable Network Devices: A Survey","author":"Zheng Changgang","year":"2023","unstructured":"Changgang Zheng, Xinpeng Hong, Damu Ding, Shay Vargaftik, Yaniv Ben-Itzhak, and Noa Zilberman. 2023. In-Network Machine Learning Using Programmable Network Devices: A Survey. IEEE Communications Surveys & Tutorials (2023)."}],"event":{"name":"ACM SIGCOMM '24: ACM SIGCOMM 2024 Conference","location":"Sydney NSW Australia","acronym":"ACM SIGCOMM '24","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2024 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672214","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651890.3672214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:12Z","timestamp":1750268952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":58,"alternative-id":["10.1145\/3651890.3672214","10.1145\/3651890"],"URL":"https:\/\/doi.org\/10.1145\/3651890.3672214","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]},"assertion":[{"value":"2024-08-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}