{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:49:13Z","timestamp":1764874153655,"version":"3.37.3"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2021B0101400001"],"award-info":[{"award-number":["2021B0101400001"]}]},{"name":"Hong Kong RGC TRS","award":["T41-603\/20-R"],"award-info":[{"award-number":["T41-603\/20-R"]}]},{"name":"GRF","award":["16213621"],"award-info":[{"award-number":["16213621"]}]},{"name":"ITF ACCESS"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62062005","62102046"],"award-info":[{"award-number":["62062005","62102046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2022JJ30618"],"award-info":[{"award-number":["2022JJ30618"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tpds.2024.3413718","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T18:20:51Z","timestamp":1718302851000},"page":"1506-1523","source":"Crossref","is-referenced-by-count":3,"title":["High-Performance Hardware Acceleration Architecture for Cross-Silo Federated Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-7801","authenticated-orcid":false,"given":"Junxue","family":"Zhang","sequence":"first","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3696-064X","authenticated-orcid":false,"given":"Xiaodian","family":"Cheng","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4393-1791","authenticated-orcid":false,"given":"Liu","family":"Yang","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8216-9683","authenticated-orcid":false,"given":"Jinbin","family":"Hu","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3238-8500","authenticated-orcid":false,"given":"Han","family":"Tian","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2587-6028","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"iSING Lab, Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3470449"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3387107"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48910-X_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14577-3_13"},{"article-title":"HAFLO: GPU-based acceleration for federated logistic regression","year":"2021","author":"Cheng","key":"ref6"},{"year":"2020","key":"ref7","article-title":"Xilinx UltraScale FPGA production table and production selection guide"},{"year":"2019","key":"ref8","article-title":"Federated AI Technology Enabler"},{"year":"2020","key":"ref9","article-title":"The GNU multiple precision arithmetic library"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378523"},{"year":"2020","key":"ref11","article-title":"NVIDIA A100"},{"year":"2022","key":"ref12","article-title":"NVIDIA H100"},{"year":"2016","key":"ref13","article-title":"NVIDIA P4"},{"year":"2020","key":"ref14","article-title":"Xilinx virtex UltraScale FPGA data sheet: DC and AC switching characteristics"},{"year":"2022","key":"ref15","article-title":"Synopsys design compiler"},{"year":"2022","key":"ref16","article-title":"Synopsys VCS"},{"year":"2022","key":"ref17","article-title":"Synopsys prime time"},{"year":"2018","key":"ref18","article-title":"Alibaba cloud F3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833648"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467210"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457241"},{"key":"ref25","first-page":"1057","article-title":"FLASH: Towards a high-performance hardware acceleration architecture for cross-silo federated learning","volume-title":"Proc. 20th USENIX Symp. Netw. Syst. Des. Implementation","author":"Zhang"},{"article-title":"Applied federated learning: Improving google keyboard query suggestions","year":"2018","author":"Yang","key":"ref26"},{"key":"ref27","first-page":"374","article-title":"Towards federated learning at scale: System design","volume-title":"Proc. Mach. Learn. Syst.","author":"Bonawitz"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2501\/IJMR-2017-050"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2787987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3082561"},{"year":"2019","key":"ref31","article-title":"netem"},{"article-title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","year":"2017","author":"Hardy","key":"ref32"},{"year":"2021","key":"ref33","article-title":"FedLearner"},{"year":"2022","key":"ref34","article-title":"TF Encrypted"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3214303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/040\/1059485"},{"year":"2019","key":"ref37","article-title":"Mellanox ConnectX-4 EN adapter card single\/dual-port 100 gigabit ethernet adapter"},{"year":"2019","key":"ref38","article-title":"Mellanox SN2100 open ethernet switch"},{"year":"2017","key":"ref39","article-title":"Intel Xeon Silver 4114 Processor"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783747"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00041"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00030"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1006\/jagm.1997.0913"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/40.502403"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1049\/ip-e.1993.0026"},{"year":"2015","key":"ref46","article-title":"Multiplier v12.0 LogiCORE IP product guide"},{"year":"2020","key":"ref47","article-title":"Xilinx UltraScale architecture DSP slice user guide"},{"year":"2020","key":"ref48","article-title":"UltraScale architecture memory resources"},{"issue":"4","key":"ref49","first-page":"2091","article-title":"AXI interconnect between four master and four slave interfaces","volume":"2","author":"Nigam","year":"2014","journal-title":"Int. J. Eng. Res. Gen. Sci"},{"article-title":"Designing high-performance video systems in 7 series FPGAs with the AXI interconnect","year":"2012","author":"Kumbhare","key":"ref50"},{"year":"2020","key":"ref51","article-title":"Timing closure user guide"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2365-6"},{"year":"2021","key":"ref53","article-title":"Super logic region SLR"},{"year":"2020","key":"ref54","article-title":"Xilinx DMA"},{"year":"2021","key":"ref55","article-title":"Laguna Registers"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/FPL53798.2021.00027"},{"year":"2019","key":"ref57","article-title":"Federated machine learning"},{"year":"2023","key":"ref58","article-title":"Amazon AWS F1"},{"year":"2023","key":"ref59","article-title":"Microsoft Azure NP"},{"year":"2023","key":"ref60","article-title":"Huawei Cloud FP1"},{"year":"2020","key":"ref61","article-title":"Xilinx alveo U250 data center accelerator card"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1002\/sec.1442"},{"year":"2019","key":"ref63","article-title":"Xilinx Virtex7 FPGAs"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.14711\/thesis-991012879963103412"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3010585"},{"year":"2019","key":"ref66","article-title":"Xilinx Zynq UltraScale MPSoCs"},{"year":"2020","key":"ref67","article-title":"Credit card cheating detection"},{"article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","year":"2017","author":"Xiao","key":"ref68"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"year":"2019","key":"ref70","article-title":"Text generation with an RNN"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref72"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref74","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan"},{"year":"2022","key":"ref75","article-title":"Hetero Fast SecureBoost"},{"key":"ref76","first-page":"493","article-title":"BatchCrypt: Efficient homomorphic encryption for cross-silo federated learning","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480070"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527415"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527393"},{"article-title":"FLASHE: Additively symmetric homomorphic encryption for cross-silo federated learning","year":"2021","author":"Jiang","key":"ref80"},{"key":"ref81","first-page":"367","article-title":"MAGE: Nearly zero-cost virtual memory for secure computation","volume-title":"Proc. 15th USENIX Symp. Operating Syst. Des. Implementation","author":"Kumar"},{"key":"ref82","first-page":"1345","article-title":"Tiara: A scalable and efficient hardware acceleration architecture for stateful layer-4 load balancing","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Zeng"},{"key":"ref83","first-page":"531","article-title":"FlowBlaze: Stateful packet processing in hardware","volume-title":"Proc. 16th USENIX Symp. Networked Syst. Des. Implementation","author":"Pontarelli"},{"key":"ref84","first-page":"973","article-title":"hXDP: Efficient software packet processing on FPGA nics","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Brunella"},{"key":"ref85","first-page":"845","article-title":"MicroRec: Efficient recommendation inference by hardware and data structure solutions","volume-title":"Proc. Mach. Learn. Syst.","author":"Jiang"},{"key":"ref86","first-page":"841","article-title":"FAERY: An fpga-accelerated embedding-based retrieval system","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Zeng"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3093234"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3676955"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/10557478\/10556815.pdf?arnumber=10556815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T05:54:29Z","timestamp":1721368469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10556815\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":88,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2024.3413718","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"type":"print","value":"1045-9219"},{"type":"electronic","value":"1558-2183"},{"type":"electronic","value":"2161-9883"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}