{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:45:02Z","timestamp":1750308302417,"version":"3.41.0"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council of Hong Kong","doi-asserted-by":"publisher","award":["11209520"],"award-info":[{"award-number":["11209520"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["4937007","4937008","5501329","5501517"],"award-info":[{"award-number":["4937007","4937008","5501329","5501517"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Gift Fund from Microsoft","award":["6906276"],"award-info":[{"award-number":["6906276"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/ton.2024.3520210","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:50:04Z","timestamp":1737571804000},"page":"1070-1085","source":"Crossref","is-referenced-by-count":0,"title":["Low-Overhead Intra-Host Container Communication With Hardware Offloading"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4482-6248","authenticated-orcid":false,"given":"Qiang","family":"Su","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6947-9740","authenticated-orcid":false,"given":"Zhixiong","family":"Niu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2021-4917","authenticated-orcid":false,"given":"Ran","family":"Shu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4014-4757","authenticated-orcid":false,"given":"Peng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4175-0097","authenticated-orcid":false,"given":"Yongqiang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6922-7244","authenticated-orcid":false,"given":"Dongsu","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6431-9868","authenticated-orcid":false,"given":"Chun","family":"Jason Xue","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9359-9571","authenticated-orcid":false,"given":"Hong","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Achieving Fast, Scalable I\/O for Virtualized Servers","year":"2023","key":"ref1"},{"volume-title":"Amazon Web Service","year":"2023","key":"ref2"},{"volume-title":"AMD Zen 4 Epyc CPU","year":"2023","key":"ref3"},{"volume-title":"Backends That Come With PyTorch","year":"2023","key":"ref4"},{"volume-title":"Baidu-Allreduce","year":"2023","key":"ref5"},{"volume-title":"Bpftrace: High-level Tracing Language for Linux Systems","year":"2023","key":"ref6"},{"volume-title":"Cilium","year":"2023","key":"ref7"},{"volume-title":"Cloud-Native Network Functions","year":"2023","key":"ref8"},{"volume-title":"Deep Learning Containers in Google Cloud","year":"2023","key":"ref9"},{"volume-title":"F-Stack: A High Performance Userspace Stack Based on FreeBSD 11.0 Stable","year":"2023","key":"ref10"},{"volume-title":"Fast Memcpy With SPDK and Intel I\/OAT DMA Engine","year":"2023","key":"ref11"},{"volume-title":"FreeFlow TCP","year":"2023","key":"ref12"},{"volume-title":"Gloo","year":"2023","key":"ref13"},{"volume-title":"GPUs Vs CPUs for Deployment of Deep Learning Models","year":"2023","key":"ref14"},{"volume-title":"Implement Mmap() for Zero Copy Receive","year":"2023","key":"ref15"},{"volume-title":"Implementing TCP Sockets Over RDMA","year":"2023","key":"ref16"},{"volume-title":"Information About the TCP Chimney Offload, Receive Side Scaling, and Network Direct Memory Access Features in Windows Server 2008","year":"2023","key":"ref17"},{"volume-title":"Intel Arria 10 Product Table","year":"2023","key":"ref18"},{"volume-title":"Intel C610 Series Chipset Datasheet","year":"2023","key":"ref19"},{"volume-title":"Intel DSA Specification","year":"2023","key":"ref20"},{"volume-title":"IOAT Benchmark","year":"2023","key":"ref21"},{"volume-title":"IO_Uring","year":"2023","key":"ref22"},{"volume-title":"ISTIO","year":"2023","key":"ref23"},{"volume-title":"Linkerd Architecture","year":"2023","key":"ref24"},{"volume-title":"Mellanox BlueField-2 DPU","year":"2023","key":"ref25"},{"volume-title":"Microsoft Azure","year":"2023","key":"ref26"},{"volume-title":"NCCL","year":"2023","key":"ref27"},{"volume-title":"Open MPI: Open Source High Performance Computing","year":"2023","key":"ref28"},{"volume-title":"Perftest","year":"2023","key":"ref29"},{"volume-title":"Run Spark Applications With Docker Using Amazon EMR 6.x","year":"2023","key":"ref30"},{"volume-title":"Seastar","year":"2023","key":"ref31"},{"volume-title":"Spark and Docker: Your Spark Development Cycle Just Got 10\u00d7 Faster!","year":"2023","key":"ref32"},{"volume-title":"TCP MMAP() Program","year":"2023","key":"ref33"},{"volume-title":"The CIFAR-10 Dataset","year":"2023","key":"ref34"},{"volume-title":"UNIX Domain Socket","year":"2023","key":"ref35"},{"volume-title":"What is Container Management and Why is It Important","year":"2023","key":"ref36"},{"volume-title":"Why Use Docker Containers for Machine Learning Development?","year":"2023","key":"ref37"},{"volume-title":"Zero-Copy TCP Receive","year":"2023","key":"ref38"},{"key":"ref39","first-page":"49","article-title":"IX: A protected dataplane operating system for high throughput and low latency","volume-title":"Proc. USENIX OSDI","author":"Belay"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544230"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404430"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00131"},{"key":"ref44","first-page":"51","article-title":"Azure accelerated networking: SmartNICs in the public cloud","volume-title":"Proc. USENIX NSDI","author":"Firestone"},{"key":"ref45","first-page":"28","article-title":"Sockets direct protocol over infiniband in clusters: is it beneficial?","volume-title":"Proc. IEEE HOTI","author":"Goldenberg"},{"key":"ref46","first-page":"135","article-title":"MegaPipe: A new programming interface for scalable network I\/O","volume-title":"Proc. USENIX OSDI","author":"Han"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405849"},{"key":"ref49","first-page":"17","article-title":"PASTE: A network programming interface for non-volatile main memory","volume-title":"Proc. USENIX NSDI","author":"Honda"},{"key":"ref50","first-page":"445","article-title":"NetVM: High performance and flexible networking using virtualization on commodity platforms","volume-title":"Proc. USENIX NSDI","author":"Hwang"},{"key":"ref51","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. USENIX OSDI","author":"Jiang"},{"key":"ref52","first-page":"1","article-title":"Datacenter RPCs can be general and fast","volume-title":"Proc. USENIX NSDI","author":"Kalia"},{"key":"ref53","first-page":"437","article-title":"Design guidelines for high performance RDMA systems","volume-title":"Proc. USENIX ATC","author":"Kalia"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872367"},{"key":"ref55","first-page":"313","article-title":"Iron: Isolating network-based CPU in container environments","volume-title":"Proc. USENIX NSDI","author":"Khalid"},{"key":"ref56","first-page":"113","article-title":"FreeFlow: Software-based virtual RDMA networking for containerized clouds","volume-title":"Proc. USENIX NSDI","author":"Kim"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098828"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446696"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456241"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342071"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/BDCloud-SocialCom-SustainCom.2016.76"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2017.2712686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872391"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2616498.2616537"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.91"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626311"},{"key":"ref67","first-page":"77","article-title":"AccelTCP: Accelerating network applications with stateful TCP offloading","volume-title":"Proc. USENIX NSDI","author":"Moon"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3206781"},{"key":"ref69","first-page":"81","article-title":"BASTION: A security enforcement network stack for container networks","volume-title":"Proc. USENIX ATC","author":"Nam"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230560"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tnet.2021.3129806"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446732"},{"key":"ref74","first-page":"87","article-title":"FlexTOE: Flexible TCP offload with fine-grained parallelism","volume-title":"Proc. USENIX NSDI","author":"Shashidhara"},{"article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405897"},{"key":"ref77","first-page":"33","article-title":"FlexSC: Flexible system call scheduling with exception-less system calls","volume-title":"Proc. USENIX OSDI","author":"Soares"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3546037.3546054"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132762"},{"key":"ref80","first-page":"111","article-title":"FileMR: Rethinking RDMA networking for scalable persistent memory","volume-title":"Proc. USENIX NSDI","author":"Yang"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005756"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/2940147.2940155"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2018.2794344"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3167132.3167240"},{"key":"ref85","first-page":"331","article-title":"Slim: OS kernel support for a low-overhead container overlay network","volume-title":"Proc. USENIX NSDI","author":"Zhuo"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11039001\/10849664.pdf?arnumber=10849664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:37:21Z","timestamp":1750268241000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849664\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":85,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/ton.2024.3520210","relation":{},"ISSN":["2998-4157"],"issn-type":[{"type":"electronic","value":"2998-4157"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}