{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:29:25Z","timestamp":1781886565714,"version":"3.54.5"},"reference-count":15,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2022,7,1]]},"DOI":"10.1109\/lca.2022.3189207","type":"journal-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T19:28:01Z","timestamp":1657222081000},"page":"49-52","source":"Crossref","is-referenced-by-count":23,"title":["FPGA-Based AI Smart NICs for Scalable Distributed AI Training Systems"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9611-5870","authenticated-orcid":false,"given":"Rui","family":"Ma","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelos","family":"Georganas","sequence":"additional","affiliation":[{"name":"Intel Corp., Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Heinecke","sequence":"additional","affiliation":[{"name":"Intel Corp., Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3339-7705","authenticated-orcid":false,"given":"Sergey","family":"Gribok","sequence":"additional","affiliation":[{"name":"Intel Corp., Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8044-1644","authenticated-orcid":false,"given":"Andrew","family":"Boutros","sequence":"additional","affiliation":[{"name":"Intel Corp., Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eriko","family":"Nurvitadhi","sequence":"additional","affiliation":[{"name":"Accelerator Architecture Lab, Intel, Hillsboro, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref2","first-page":"10271","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Rouhani"},{"key":"ref3","first-page":"51","article-title":"Azure accelerated networking: SmartNICs in the public cloud","volume-title":"Proc. 15th USENIX Conf\/ Networked Syst. Des. Implementation","author":"Firestone"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2021.3071607"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PDP50117.2020.00022"},{"key":"ref8","first-page":"279","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proc. 46th Int. Symp. Comput. Architecture","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3039835"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00047"},{"key":"ref11","article-title":"NVidia GPUDirect RDMA","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref13","first-page":"451","article-title":"Training DNNs with hybrid block floating point","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Drumond"},{"key":"ref14","article-title":"Inter-kernel links for direct inter-FPGA communication","author":"Balle","year":"2020","journal-title":"Intel White Paper (WP-01305\u20131.0)"},{"key":"ref15","article-title":"Intel open programmable acceleration engine (OPAE)","year":"2022"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10208\/9810321\/09817635.pdf?arnumber=9817635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T04:41:16Z","timestamp":1706762476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9817635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,1]]},"references-count":15,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2022.3189207","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,1]]}}}