{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:18:39Z","timestamp":1772608719570,"version":"3.50.1"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Compute-Flow-Architecture"},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["66150"],"award-info":[{"award-number":["66150"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-76RL01830"],"award-info":[{"award-number":["DE-AC05-76RL01830"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2021,12,1]]},"DOI":"10.1109\/tpds.2021.3081074","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T20:07:43Z","timestamp":1621454863000},"page":"2880-2892","source":"Crossref","is-referenced-by-count":24,"title":["ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3727-2889","authenticated-orcid":false,"given":"Cheng","family":"Tan","sequence":"first","affiliation":[]},{"given":"Chenhao","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Tong","family":"Geng","sequence":"additional","affiliation":[]},{"given":"Andres","family":"Marquez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9452-120X","authenticated-orcid":false,"given":"Antonino","family":"Tumeo","sequence":"additional","affiliation":[]},{"given":"Kevin","family":"Barker","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3734-9137","authenticated-orcid":false,"given":"Ang","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.77"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2386883"},{"key":"ref71","article-title":"The hammerBlade: An ML-optimized supercomputer for ML and graphs","author":"taylor","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021742"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.2172\/1473756"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2940190"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2012.6412142"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2011.2126608"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2997638"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwu060"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934644"},{"key":"ref33","article-title":"Particle simulation using CUDA","author":"green","year":"2010"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00021"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/978-3-540-30218-6_19","article-title":"Open MPI: Goals, concept, and design of a next generation MPI implementation","author":"gabriel","year":"2004","journal-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2200\/S00209ED1V01Y200907CAC008"},{"key":"ref36","first-page":"10","article-title":"1.1 computing’s energy problem (and what we can do about it)","author":"horowitz","year":"2014","journal-title":"Proc IEEE Int Solid-State Circuits Conf Digest Tech Papers"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref34","first-page":"1","article-title":"Branch-aware loop mapping on CGRAs","author":"hamzeh","year":"2014","journal-title":"Proc 51st Annu Des Automat Conf"},{"key":"ref60","first-page":"3","article-title":"Tackling exascale software challenges in molecular dynamics simulations with GROMACS","author":"p\u00e1ll","year":"2015","journal-title":"Proc Int Conf Exascale Appl Software"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810122"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669160"},{"key":"ref63","article-title":"Polybench: The polyhedral benchmark suite","author":"pouchet","year":"2012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3057203"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080256"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2019.0066"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853195"},{"key":"ref66","article-title":"Structural simulation toolkit (SST)","author":"rodrigues","year":"2016"},{"key":"ref29","article-title":"Fast graph representation learning with PyTorch geometric","author":"fey","year":"2019"},{"key":"ref67","article-title":"The future of computing beyond Moore’s law","volume":"378","author":"shalf","year":"2020","journal-title":"Philosophical Trans Roy Soc A"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.9"},{"key":"ref69","first-page":"381","article-title":"OpenCGRA: An open-source unified framework for modeling, testing, and evaluating CGRAs","author":"tan","year":"0","journal-title":"Proc IEEE 38th Int Conf Comput Des"},{"key":"ref2","year":"2017"},{"key":"ref1","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007078442"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1145\/1103845.1094852","article-title":"X10: An object-oriented approach to non-uniform cluster computing","volume":"40","author":"charles","year":"2005","journal-title":"ACM SIGPLAN Notices"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91734-4_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2012.7476487"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/272536"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2397832"},{"key":"ref51","article-title":"Exascale applications in seismic hazard analysis","author":"maechling","year":"2018"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2013.0387"},{"key":"ref58","article-title":"NVIDIA DGX-2H the world’s most powerful system for the most complex AI challenges","year":"2018"},{"key":"ref57","article-title":"NVIDIA DGX-1 system architecture","year":"2017"},{"key":"ref56","article-title":"NVIDIA collective communications library (NCCL-V2)","year":"0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522739"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.28"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/N-SSC.2006.4785860"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/GREENCOMP.2010.5598316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1993.698567"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkn201"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3155284.3018756"},{"key":"ref14","first-page":"509","article-title":"Scientific computing on bulk synchronous parallel architectures","volume":"1","author":"bisseling","year":"0"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","article-title":"Cilk: An efficient multithreaded runtime system","volume":"37","author":"blumofe","year":"1996","journal-title":"J Parallel Distrib Comput"},{"key":"ref16","article-title":"GASNet specification v1. 8.1","author":"bonachea","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2172\/1477359"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173177"},{"key":"ref19","first-page":"1","article-title":"Parallel breadth-first search on distributed memory systems","author":"bulu\u00e7","year":"2011","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal"},{"key":"ref4","year":"2018"},{"key":"ref3","year":"2018"},{"key":"ref6","year":"2020"},{"key":"ref5","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00049"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/NOCS.2007.34"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2015.2465905"},{"key":"ref9","article-title":"BOOM: Data-centric programming in the datacenter","author":"alvaro","year":"2009","journal-title":"Tech Rep TR-UCB\/EECS-2009–113"},{"key":"ref46","article-title":"Introducing big basin: Our next-generation AI hardware","author":"lee","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref48","first-page":"99","article-title":"A deep reinforcement learning framework for architectural exploration: A routerless NoC case study","author":"lin","year":"2018","journal-title":"Proc IEEE Int Symp High Perform Comput Archit"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2928289"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062262"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2016.0013"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704670"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9445716\/9436051-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9445716\/09436051.pdf?arnumber=9436051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:25Z","timestamp":1652194225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9436051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,1]]},"references-count":79,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3081074","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,1]]}}}