{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:55:36Z","timestamp":1773194136821,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,17]]},"DOI":"10.1145\/3579371.3589348","type":"proceedings-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T20:25:28Z","timestamp":1686947128000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":48,"title":["MTIA: First Generation Silicon Targeting Meta's Recommendation Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0128-298X","authenticated-orcid":false,"given":"Amin","family":"Firoozshahian","sequence":"first","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2335-2711","authenticated-orcid":false,"given":"Joel","family":"Coburn","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2316-2595","authenticated-orcid":false,"given":"Roman","family":"Levenstein","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3622-423X","authenticated-orcid":false,"given":"Rakesh","family":"Nattoji","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8996-6348","authenticated-orcid":false,"given":"Ashwin","family":"Kamath","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0219-371X","authenticated-orcid":false,"given":"Olivia","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8751-1206","authenticated-orcid":false,"given":"Gurdeepak","family":"Grewal","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6062-0867","authenticated-orcid":false,"given":"Harish","family":"Aepala","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8791-6365","authenticated-orcid":false,"given":"Bhasker","family":"Jakka","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5074-3980","authenticated-orcid":false,"given":"Bob","family":"Dreyer","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7030-155X","authenticated-orcid":false,"given":"Adam","family":"Hutchin","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0915-810X","authenticated-orcid":false,"given":"Utku","family":"Diril","sequence":"additional","affiliation":[{"name":"Rivos Inc., Mountain View, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3540-5311","authenticated-orcid":false,"given":"Krishnakumar","family":"Nair","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1267-6887","authenticated-orcid":false,"given":"Ehsan K.","family":"Aredestani","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6059-0490","authenticated-orcid":false,"given":"Martin","family":"Schatz","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8513-9566","authenticated-orcid":false,"given":"Yuchen","family":"Hao","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0996-3907","authenticated-orcid":false,"given":"Rakesh","family":"Komuravelli","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2766-8114","authenticated-orcid":false,"given":"Kunming","family":"Ho","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1940-326X","authenticated-orcid":false,"given":"Sameer","family":"Abu Asal","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0214-0105","authenticated-orcid":false,"given":"Joe","family":"Shajrawi","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2700-2570","authenticated-orcid":false,"given":"Kevin","family":"Quinn","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9729-8497","authenticated-orcid":false,"given":"Nagesh","family":"Sreedhara","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6927-9203","authenticated-orcid":false,"given":"Pankaj","family":"Kansal","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6261-2407","authenticated-orcid":false,"given":"Willie","family":"Wei","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6003-2253","authenticated-orcid":false,"given":"Dheepak","family":"Jayaraman","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2861-7800","authenticated-orcid":false,"given":"Linda","family":"Cheng","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0876-9378","authenticated-orcid":false,"given":"Pritam","family":"Chopda","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9379-7706","authenticated-orcid":false,"given":"Eric","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6348-1276","authenticated-orcid":false,"given":"Ajay","family":"Bikumandla","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1400-1066","authenticated-orcid":false,"given":"Arun","family":"Karthik Sengottuvel","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9774-7678","authenticated-orcid":false,"given":"Krishna","family":"Thottempudi","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1786-9534","authenticated-orcid":false,"given":"Ashwin","family":"Narasimha","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9873-5470","authenticated-orcid":false,"given":"Brian","family":"Dodds","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6858-1655","authenticated-orcid":false,"given":"Cao","family":"Gao","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7010-2939","authenticated-orcid":false,"given":"Jiyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5801-2090","authenticated-orcid":false,"given":"Mohammed","family":"Al-Sanabani","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8014-4226","authenticated-orcid":false,"given":"Ana","family":"Zehtabioskuie","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0523-4767","authenticated-orcid":false,"given":"Jordan","family":"Fix","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6515-6271","authenticated-orcid":false,"given":"Hangchen","family":"Yu","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4666-6938","authenticated-orcid":false,"given":"Richard","family":"Li","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2482-6649","authenticated-orcid":false,"given":"Kaustubh","family":"Gondkar","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3450-7362","authenticated-orcid":false,"given":"Jack","family":"Montgomery","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7628-0809","authenticated-orcid":false,"given":"Mike","family":"Tsai","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5171-6235","authenticated-orcid":false,"given":"Saritha","family":"Dwarakapuram","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3495-9330","authenticated-orcid":false,"given":"Sanjay","family":"Desai","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1352-3161","authenticated-orcid":false,"given":"Nili","family":"Avidan","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7316-7063","authenticated-orcid":false,"given":"Poorvaja","family":"Ramani","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3837-4273","authenticated-orcid":false,"given":"Karthik","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4199-0434","authenticated-orcid":false,"given":"Ajit","family":"Mathews","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1202-3012","authenticated-orcid":false,"given":"Sethu","family":"Gopal","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6102-2903","authenticated-orcid":false,"given":"Maxim","family":"Naumov","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8069-4910","authenticated-orcid":false,"given":"Vijay","family":"Rao","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1256-8179","authenticated-orcid":false,"given":"Krishna","family":"Noru","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5849-5480","authenticated-orcid":false,"given":"Harikrishna","family":"Reddy","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9695-5208","authenticated-orcid":false,"given":"Prahlad","family":"Venkatapuram","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5375-2139","authenticated-orcid":false,"given":"Alexis","family":"Bjorlin","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Synthesis Lectures on Computer Architecture","author":"Sze V.","year":"2020","unstructured":"V. Sze , Y. Chen , T. Yang , and J.S. Emer , Efficient Processing of Deep Neural Networks , Synthesis Lectures on Computer Architecture , Morgan & Claypool Publishers , 2020 . V. Sze, Y. Chen, T. Yang, and J.S. Emer, Efficient Processing of Deep Neural Networks, Synthesis Lectures on Computer Architecture, Morgan & Claypool Publishers, 2020."},{"key":"e_1_3_2_1_2_1","volume-title":"Buffets: An efficient and composable storage idiom for explicit decoupled data orchestration,\" in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS)","author":"Pellauer M.","year":"2019","unstructured":"M. Pellauer , Y. S. Shao , J. Clemons , N. Crago , K. Hegde , R. Venkatesan , S. W. Keckler , C. W. Fletcher , and J. Emer , \" Buffets: An efficient and composable storage idiom for explicit decoupled data orchestration,\" in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS) , 2019 . M. Pellauer, Y. S. Shao, J. Clemons, N. Crago, K. Hegde, R. Venkatesan, S. W. Keckler, C. W. Fletcher, and J. Emer, \"Buffets: An efficient and composable storage idiom for explicit decoupled data orchestration,\" in Proceedings of Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2019."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of International Symposium on Computer Architecture (ISCA)","author":"Chen Y.-H.","year":"2016","unstructured":"Y.-H. Chen , J. Emer , and V. Sze , Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks , in Proceedings of International Symposium on Computer Architecture (ISCA) , 2016 . Y.-H. Chen, J. Emer, and V. Sze, Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks, in Proceedings of International Symposium on Computer Architecture (ISCA), 2016."},{"issue":"1","key":"e_1_3_2_1_4_1","volume":"51","author":"Chen Y.-H.","year":"2017","unstructured":"Y.-H. Chen , T. Krishna , J. Emer , and V. Sze , Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks IEEE Journal of Solid-State Circuits (JSSC) , 51 ( 1 ), 2017 . Y.-H. Chen, T. Krishna, J. Emer, and V. Sze, Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks IEEE Journal of Solid-State Circuits (JSSC), 51(1), 2017.","journal-title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks IEEE Journal of Solid-State Circuits (JSSC)"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.1987.1052667"},{"key":"e_1_3_2_1_6_1","volume-title":"Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices,\" in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS)","author":"Chen Y.-H.","year":"2019","unstructured":"Y.-H. Chen , T.-J. Yang , J. Emer , and V. Sze , \" Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices,\" in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS) , 2019 . Y.-H. Chen, T.-J. Yang, J. Emer, and V. Sze, \"Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices,\" in IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), 2019."},{"key":"e_1_3_2_1_7_1","volume-title":"Synthesis Lectures on Computer Architecture","author":"Krishna T.","year":"2020","unstructured":"T. Krishna , H. Kwon , A. Parashar , M. Pellauer , and A. Samajdar , Data Orchestration in Deep Learning Accelerators , Synthesis Lectures on Computer Architecture , Morgan & Claypool Publishers , 2020 . T. Krishna, H. Kwon, A. Parashar, M. Pellauer, and A. Samajdar, Data Orchestration in Deep Learning Accelerators, Synthesis Lectures on Computer Architecture, Morgan & Claypool Publishers, 2020."},{"key":"e_1_3_2_1_8_1","volume-title":"June","author":"Jouppi N. P.","year":"2017","unstructured":"N. P. Jouppi , C. Young , N. Patil , D. Patterson , G. Agrawal , R. Bajwa , S. Bates , S. Bhatia , N. Boden , A. Borchers , R. Boyle , P.-L. Cantin , C. Chao , C. Clark , J. Coriell , M. Daley , M. Dau , J. Dean , B. Gelb , T. V. Ghaemmaghami , R. Gottipati , W. Gulland , R. Hagmann , C. R. Ho , D. Hogberg , J. Hu , R. Hundt , D. Hurt , J. Ibarz , A. Jaffey , A. Jaworski , A. Kaplan , H. Khaitan , D. Killebrew , A. Koch , N. Kumar , S. Lacy , J. Laudon , J. Law , D. Le , C. Leary , Z. Liu , K. Lucke , A. Lundin , G. MacKean , A. Maggiore , M. Mahony , K. Miller , R. Nagarajan , R. Narayanaswami , R. Ni , K. Nix , T. Norrie , M. Omernick , N. Penukonda , A. Phelps , J. Ross , M. Ross , A. Salek , E. Samadiani , C. Severn , G. Sizikov , M. Snelham , J. Souter , D. Steinberg , A. Swing , M. Tan , G. Thorson , B. Tian , H. Toma , E. Tuttle , V. Vasudevan , R. Walter , W. Wang , E. Wilcox , and D. H. Yoon , \" In-datacenter performance analysis of a tensor processing unit,\" in Proceedings of the International Symposium on Computer Architecture (ISCA) , June 2017 . N. P. Jouppi, C. Young, N. Patil, D. Patterson, G. Agrawal, R. Bajwa, S. Bates, S. Bhatia, N. Boden, A. Borchers, R. Boyle, P.-L. Cantin, C. Chao, C. Clark, J. Coriell, M. Daley, M. Dau, J. Dean, B. Gelb, T. V. Ghaemmaghami, R. Gottipati, W. Gulland, R. Hagmann, C. R. Ho, D. Hogberg, J. Hu, R. Hundt, D. Hurt, J. Ibarz, A. Jaffey, A. Jaworski, A. Kaplan, H. Khaitan, D. Killebrew, A. Koch, N. Kumar, S. Lacy, J. Laudon, J. Law, D. Le, C. Leary, Z. Liu, K. Lucke, A. Lundin, G. MacKean, A. Maggiore, M. Mahony, K. Miller, R. Nagarajan, R. Narayanaswami, R. Ni, K. Nix, T. Norrie, M. Omernick, N. Penukonda, A. Phelps, J. Ross, M. Ross, A. Salek, E. Samadiani, C. Severn, G. Sizikov, M. Snelham, J. Souter, D. Steinberg, A. Swing, M. Tan, G. Thorson, B. Tian, H. Toma, E. Tuttle, V. Vasudevan, R. Walter, W. Wang, E. Wilcox, and D. H. Yoon, \"In-datacenter performance analysis of a tensor processing unit,\" in Proceedings of the International Symposium on Computer Architecture (ISCA), June 2017."},{"key":"e_1_3_2_1_9_1","unstructured":"https:\/\/zephyrproject.org  https:\/\/zephyrproject.org"},{"key":"e_1_3_2_1_10_1","unstructured":"M. Anderson B. Chen S. Chen S. Deng J. Fix M. Gschwind A. Kalaiah C. Kim J. Lee J. Liang H. Liu Y. Lu J. Montgomery A. Moorthy S. Nadathur S. Naghshineh A. Nayak J. Park C. Petersen M. Schatz N. Sundaram B. Tang P. Tang A. Yang J. Yu H. Yuen Y. Zhang A. Anbudurai V. Balan H. Bojja J. Boyd M. Breitbach C. Caldato A. Calvo G. Catron S. Chandwani P. Christeas B. Cottel B. Coutinho A. Dalli A. Dhanotia O. Duncan R. Dzhabarov S. Elmir C. Fu W. Fu M. Fulthorp A. Gangidi N. Gibson S. Gordon B. Padilla Hernandez D. Ho Y. Huang O. Johansson S. Juluri S. Kanaujia M. Kesarkar J. Killinger B. Kim R. Kulkarni M. Lele Huayu Li Huamin Li Y. Li C. Liu J. Liu B. Maher C. Mallipedi S. Mangla K.K. Matam J. Mehta S. Mehta C. Mitchell B. Muthiah N. Nagarkatte A. Narasimha B. Nguyen T. Ortiz S. Padmanabha D. Pan A. Poojary Y. Qi O. Raginel D. Rajagopal T. Rice C. Ross N. Rotem S. Russ K. Shah B. Shan H. Shen P. Shetty K. Skandakumaran K. Srinivasan R. Sumbaly M. Tauberg M. Tzur S. Verma H. Wang M. Wang B. Wei A. Xia C. Xu M. Yang K. Zhang R. Zhang M. Zhao W. Zhao R. Zhu A. Mathews L. Qiao M. Smelyanskiy B. Jia V. Rao. \"First-Generation Inference Accelerator Deployment at Facebook \" in Arxiv 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2107.04140 unpublished.  M. Anderson B. Chen S. Chen S. Deng J. Fix M. Gschwind A. Kalaiah C. Kim J. Lee J. Liang H. Liu Y. Lu J. Montgomery A. Moorthy S. Nadathur S. Naghshineh A. Nayak J. Park C. Petersen M. Schatz N. Sundaram B. Tang P. Tang A. Yang J. Yu H. Yuen Y. Zhang A. Anbudurai V. Balan H. Bojja J. Boyd M. Breitbach C. Caldato A. Calvo G. Catron S. Chandwani P. Christeas B. Cottel B. Coutinho A. Dalli A. Dhanotia O. Duncan R. Dzhabarov S. Elmir C. Fu W. Fu M. Fulthorp A. Gangidi N. Gibson S. Gordon B. Padilla Hernandez D. Ho Y. Huang O. Johansson S. Juluri S. Kanaujia M. Kesarkar J. Killinger B. Kim R. Kulkarni M. Lele Huayu Li Huamin Li Y. Li C. Liu J. Liu B. Maher C. Mallipedi S. Mangla K.K. Matam J. Mehta S. Mehta C. Mitchell B. Muthiah N. Nagarkatte A. Narasimha B. Nguyen T. Ortiz S. Padmanabha D. Pan A. Poojary Y. Qi O. Raginel D. Rajagopal T. Rice C. Ross N. Rotem S. Russ K. Shah B. Shan H. Shen P. Shetty K. Skandakumaran K. Srinivasan R. Sumbaly M. Tauberg M. Tzur S. Verma H. Wang M. Wang B. Wei A. Xia C. Xu M. Yang K. Zhang R. Zhang M. Zhao W. Zhao R. Zhu A. Mathews L. Qiao M. Smelyanskiy B. Jia V. Rao. \"First-Generation Inference Accelerator Deployment at Facebook \" in Arxiv 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2107.04140 unpublished."},{"key":"e_1_3_2_1_11_1","unstructured":"J. Ehlen J. Clow B. Wei D. Chong \"Facebook Multi-node Server Platform: Yosemite V2 Design Specification \" Open Compute Project https:\/\/www.opencompute.org\/documents\/facebook-multi-node-server-platform-yosemite-v2-design-specification  J. Ehlen J. Clow B. Wei D. Chong \"Facebook Multi-node Server Platform: Yosemite V2 Design Specification \" Open Compute Project https:\/\/www.opencompute.org\/documents\/facebook-multi-node-server-platform-yosemite-v2-design-specification"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the International Symposium on Computer Architecture (ISCA)","author":"Mudigere D.","year":"2022","unstructured":"D. Mudigere , Y. Hao , J. Huang , Z. Jia , A. Tulloch , S. Sridharan , X. Liu , M. Ozdal , J. Nie , J. Park , L. Luo , J. Yang , L. Gao , D. Ivchenko , A. Basant , Y. Hu , J. Yang , E. K. Ardestani , X. Wang , R. Komuravelli , C.H. Chu , S. Yilmaz , H. Li , J. Qian , Z. Feng , Y. Ma , J. Yang , E. Wen , H. Li , L. Yang , C. Sun , W. Zhao , D. Melts , K. Dhulipala , KR. Kishore , T. Graf , A Eisenman , K. K. Matam , A. Gangidi , G. J. Chen , M. Krishnan , A. Nayak , K Nair , B. Muthiah , M. khorashadi, P. Bhattacharya , P. Lapukhov , M. Naumov , A. Mathews , L. Qiao , M. Smelyanskiy , B. Jia , V. Rao , \" Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models ,\" in Proceedings of the International Symposium on Computer Architecture (ISCA) , June 2022 . D. Mudigere, Y. Hao, J. Huang, Z. Jia, A. Tulloch, S. Sridharan, X. Liu, M. Ozdal, J. Nie, J. Park, L. Luo, J. Yang, L. Gao, D. Ivchenko, A. Basant, Y. Hu, J. Yang, E. K. Ardestani, X. Wang, R. Komuravelli, C.H. Chu, S. Yilmaz, H. Li, J. Qian, Z. Feng, Y. Ma, J. Yang, E. Wen, H. Li, L. Yang, C. Sun, W. Zhao, D. Melts, K. Dhulipala, KR. Kishore, T. Graf, A Eisenman, K. K. Matam, A. Gangidi, G. J. Chen, M. Krishnan, A. Nayak, K Nair, B. Muthiah, M. khorashadi, P. Bhattacharya, P. Lapukhov, M. Naumov, A. Mathews, L. Qiao, M. Smelyanskiy, B. Jia, V. Rao, \"Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models,\" in Proceedings of the International Symposium on Computer Architecture (ISCA), June 2022."},{"key":"e_1_3_2_1_13_1","unstructured":"M. Haken J. Clow Y. Li B. Wei D. Chong T Ky \"Yosemite V3: Facebook Multi-node Server Platform Design Specification\" Open Compute Project https:\/\/www.opencompute.org\/documents\/ocp-yosemite-v3-platform-design-specification-1v16-pdf  M. Haken J. Clow Y. Li B. Wei D. Chong T Ky \"Yosemite V3: Facebook Multi-node Server Platform Design Specification\" Open Compute Project https:\/\/www.opencompute.org\/documents\/ocp-yosemite-v3-platform-design-specification-1v16-pdf"},{"key":"e_1_3_2_1_14_1","unstructured":"GemmBench. [Online]. Available: https:\/\/https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/GemmBench.cpp  GemmBench. [Online]. Available: https:\/\/https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/GemmBench.cpp"},{"key":"e_1_3_2_1_15_1","unstructured":"TableBatchedEmbeddingBagBench (TBEBench). [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/TBEBench.cpp  TableBatchedEmbeddingBagBench (TBEBench). [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/TBEBench.cpp"},{"key":"e_1_3_2_1_16_1","unstructured":"M. Naumov D. Mudigere H. M. Shi J. Huang N. Sundaraman J. Park X. Wang U. Gupta C. Wu A.G. Azzolini D. Dzhulgakov A. Mallevich I. Cherniavskii Y. Lu R. Krishnamoorthi A. Yu V. Kondratenko S. Pereira X. Chen W. Chen V. Rao B. Jia L. Xiong M. Smelyanskiy \"Deep Learning Recommendation Model for Personalization and Recommendation Systems \" in Arxiv 2021 [Online]. Available: https:\/\/arxiv.org\/abs\/1906.00091 unpublished  M. Naumov D. Mudigere H. M. Shi J. Huang N. Sundaraman J. Park X. Wang U. Gupta C. Wu A.G. Azzolini D. Dzhulgakov A. Mallevich I. Cherniavskii Y. Lu R. Krishnamoorthi A. Yu V. Kondratenko S. Pereira X. Chen W. Chen V. Rao B. Jia L. Xiong M. Smelyanskiy \"Deep Learning Recommendation Model for Personalization and Recommendation Systems \" in Arxiv 2021 [Online]. Available: https:\/\/arxiv.org\/abs\/1906.00091 unpublished"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Symposium on High Performance Computer Architecture (HPCA)","author":"Gupta U.","year":"2020","unstructured":"U. Gupta , C. Wu , X. Wang , M. Naumov , B. Reagen , D. Brooks , B. Cottel , K. Hazelwood , M. Hempstead , B. Jia , H.S. Lee , A. Malevich , D. Mudigere , M. Smelyanskiy , L. Xiong , X. Zhang , \" The Architectural Implications of Facebook's DNN-based Personalized Recommendation ,\" in Proceedings of the International Symposium on High Performance Computer Architecture (HPCA) , February 2020 . U. Gupta, C. Wu, X. Wang, M. Naumov, B. Reagen, D. Brooks, B. Cottel, K. Hazelwood, M. Hempstead, B. Jia, H.S.Lee, A. Malevich, D. Mudigere, M. Smelyanskiy, L. Xiong, X. Zhang, \"The Architectural Implications of Facebook's DNN-based Personalized Recommendation,\" in Proceedings of the International Symposium on High Performance Computer Architecture (HPCA), February 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"Characterization, Performance Optimizations and Hardware Implications,\" in Arxiv","author":"Park J.","year":"2018","unstructured":"J. Park , M. Naumov , P. Basu , S. Deng , A. Kalaiah , D. Khudia , J. Law , P. Malani , Andrey Malevich , Satish Nadathur , Juan Pino , Martin Schatz , Alexander Sidorov , Viswanath Sivakumar , Andrew Tulloch , Xiaodong Wang , Yiming Wu , Hector Yuen , Utku Diril , D. Dzhulgakov , Kim Hazelwood , Bill Jia , Yangqing Jia , Lin Qiao , Vijay Rao , Nadav Rotem , Sungjoo Yoo , Mikhail Smelyanskiy \"Deep Learning Inference in Facebook Data Centers : Characterization, Performance Optimizations and Hardware Implications,\" in Arxiv , 2018 , [Online]. Available: https:\/\/arxiv.org\/abs\/1811.09886 J. Park, M. Naumov, P. Basu, S. Deng, A. Kalaiah, D. Khudia, J. Law, P. Malani, Andrey Malevich, Satish Nadathur, Juan Pino, Martin Schatz, Alexander Sidorov, Viswanath Sivakumar, Andrew Tulloch, Xiaodong Wang, Yiming Wu, Hector Yuen, Utku Diril, D. Dzhulgakov, Kim Hazelwood, Bill Jia, Yangqing Jia, Lin Qiao, Vijay Rao, Nadav Rotem, Sungjoo Yoo, Mikhail Smelyanskiy \"Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications,\" in Arxiv, 2018, [Online]. Available: https:\/\/arxiv.org\/abs\/1811.09886"},{"key":"e_1_3_2_1_19_1","volume-title":"Practical Program Capture and Transformation of Deep Learning in Python,\" in Arxiv","author":"Reed J. K.","year":"2022","unstructured":"J. K. Reed , Z. DeVito , H. He , A. Ussery , J. Ansel , \"Torch.fx : Practical Program Capture and Transformation of Deep Learning in Python,\" in Arxiv , 2022 , [Online]. Available: https:\/\/arxiv.org\/abs\/2112.08429 J. K. Reed, Z. DeVito, H. He, A. Ussery, J. Ansel, \"Torch.fx: Practical Program Capture and Transformation of Deep Learning in Python,\" in Arxiv, 2022, [Online]. Available: https:\/\/arxiv.org\/abs\/2112.08429"},{"key":"e_1_3_2_1_20_1","unstructured":"https:\/\/pytorch.org\/docs\/stable\/fx.html  https:\/\/pytorch.org\/docs\/stable\/fx.html"},{"key":"e_1_3_2_1_21_1","volume-title":"a compilation framework for lifelong program analysis & transformation,\" in Proceedings of International Symposium on Code Generation and Optimization","author":"Lattner C.","year":"2004","unstructured":"C. Lattner , V. Adve , \"LLVM : a compilation framework for lifelong program analysis & transformation,\" in Proceedings of International Symposium on Code Generation and Optimization , 2004 . C. Lattner, V. Adve, \"LLVM: a compilation framework for lifelong program analysis & transformation,\" in Proceedings of International Symposium on Code Generation and Optimization, 2004."},{"key":"e_1_3_2_1_22_1","unstructured":"https:\/\/llvm.org\/docs\/LangRef.html  https:\/\/llvm.org\/docs\/LangRef.html"},{"key":"e_1_3_2_1_23_1","unstructured":"https:\/\/github.com\/riscv\/riscv-v-spec  https:\/\/github.com\/riscv\/riscv-v-spec"},{"key":"e_1_3_2_1_24_1","unstructured":"BatchGemmBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/BatchGemmBench.cpp  BatchGemmBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/BatchGemmBench.cpp"},{"key":"e_1_3_2_1_25_1","unstructured":"ConcatBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/ConcatBench.cpp  ConcatBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/ConcatBench.cpp"},{"key":"e_1_3_2_1_26_1","unstructured":"TransposeBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/TransposeBench.cpp  TransposeBench. [Online]. Available: https:\/\/github.com\/pytorch\/glow\/blob\/master\/tests\/benchmark\/TransposeBench.cpp"}],"event":{"name":"ISCA '23: 50th Annual International Symposium on Computer Architecture","location":"Orlando FL USA","acronym":"ISCA '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE"]},"container-title":["Proceedings of the 50th Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579371.3589348","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:40Z","timestamp":1750178800000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579371.3589348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":26,"alternative-id":["10.1145\/3579371.3589348","10.1145\/3579371"],"URL":"https:\/\/doi.org\/10.1145\/3579371.3589348","relation":{},"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"2023-06-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}