{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:48:52Z","timestamp":1753886932011,"version":"3.37.3"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF CRI Award","doi-asserted-by":"publisher","award":["1512937"],"award-info":[{"award-number":["1512937"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF SHF Award","doi-asserted-by":"publisher","award":["1527065"],"award-info":[{"award-number":["1527065"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF SHF","doi-asserted-by":"publisher","award":["1909661"],"award-info":[{"award-number":["1909661"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"DARPA SDH Award","doi-asserted-by":"publisher","award":["FA8650-18-2-7863"],"award-info":[{"award-number":["FA8650-18-2-7863"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005801","name":"Facebook","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005801","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tcad.2021.3103825","type":"journal-article","created":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T20:15:12Z","timestamp":1628626512000},"page":"1620-1635","source":"Crossref","is-referenced-by-count":8,"title":["A Tensor Processing Framework for CPU-Manycore Heterogeneous Systems"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4551-2002","authenticated-orcid":false,"given":"Lin","family":"Cheng","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"given":"Peitian","family":"Pan","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"given":"Zhongyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6083-6251","authenticated-orcid":false,"given":"Krithik","family":"Ranjan","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1688-6358","authenticated-orcid":false,"given":"Jack","family":"Weber","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"given":"Bandhav","family":"Veluri","sequence":"additional","affiliation":[{"name":"Paul Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}]},{"given":"Seyed Borna","family":"Ehsani","sequence":"additional","affiliation":[{"name":"Paul Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}]},{"given":"Max","family":"Ruttenberg","sequence":"additional","affiliation":[{"name":"Paul Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3165-4213","authenticated-orcid":false,"given":"Dai Cheol","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, USA"}]},{"given":"Preslav","family":"Ivanov","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4587-8947","authenticated-orcid":false,"given":"Dustin","family":"Richmond","sequence":"additional","affiliation":[{"name":"Paul Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4074-6347","authenticated-orcid":false,"given":"Michael B.","family":"Taylor","sequence":"additional","affiliation":[{"name":"Paul Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-0308","authenticated-orcid":false,"given":"Zhiru","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2835-667X","authenticated-orcid":false,"given":"Christopher","family":"Batten","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA"}]}],"member":"263","reference":[{"journal-title":"Benchmarking tpu gpu and cpu platforms for deep learning","year":"2019","author":"wang","key":"ref39"},{"journal-title":"Deep residual learning for image recognition","year":"2015","author":"he","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01891"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488748"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00068"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00062"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2019.8778031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2006.41"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830800"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"journal-title":"ATen A TENsor Library for C++11","year":"2020","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11515-8_3"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.23"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2017.36"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2003.1234253"},{"key":"ref20","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"journal-title":"cuGraph—GPU Graph Analytics","year":"2020","key":"ref22"},{"key":"ref21","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of the 5th Symp on Oper Syst Design and Implementation (OSDI)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750407"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310765"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00041"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/357401.357403"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192379"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2019.2928962"},{"journal-title":"Ampere Maxes Out at 128 Cores","year":"2020","author":"wheeler","key":"ref10"},{"journal-title":"Thunderx3’s Cloudburst of Threads Marvell Previews 96-Core 384-Thread Arm Server Processor","year":"2020","author":"halfhill","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2019.2953847"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2007.4378780"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2638459"},{"journal-title":"Epiphany-v A 1024 processor 64-bit risc system-on-chip","year":"2016","author":"olofsson","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3045564"},{"key":"ref17","article-title":"RTX on: The NVIDIA turing architecture","author":"burgess","year":"2019","journal-title":"Proc Symp High Perform Chips (Hot Chips)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875649"},{"key":"ref19","first-page":"1","article-title":"CuPy: A NumPy-compatible library for NVIDIA GPU calculations","author":"okuta","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2007.4378783"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2010.5434077"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062927"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2013.7478320"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477491"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2008.4523070"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1168857.1168877"},{"journal-title":"Knights Landing Reshapes HPC","year":"2015","author":"kanter","key":"ref9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080256"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310759"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3192366.3192393"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"journal-title":"TVM An automated end-to-end optimizing compiler for deep learning","year":"2018","author":"chen","key":"ref44"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/9778249\/9509755-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/9778249\/09509755.pdf?arnumber=9509755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,13]],"date-time":"2022-06-13T20:21:00Z","timestamp":1655151660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9509755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":52,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2021.3103825","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"type":"print","value":"0278-0070"},{"type":"electronic","value":"1937-4151"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}