{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:27:10Z","timestamp":1759134430304,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001851","name":"Ministry of Earth Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001851","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,5,1]]},"DOI":"10.1109\/tpds.2016.2616314","type":"journal-article","created":{"date-parts":[[2016,10,11]],"date-time":"2016-10-11T18:34:05Z","timestamp":1476210845000},"page":"1518-1534","source":"Crossref","is-referenced-by-count":12,"title":["The Unicorn Runtime: Efficient Distributed Shared Memory Programming for Hybrid CPU-GPU Clusters"],"prefix":"10.1109","volume":"28","author":[{"given":"Tarun","family":"Beri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sorav","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subodh","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"An Introduction to the Partitioned Global Address Space (PGAS) Programming Model","year":"2010","author":"stitt","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(98)00093-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/209937.209958"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/169627.169724"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/0471478369"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807611"},{"key":"ref37","article-title":"A user&#x2019;s guide to PVM parallel virtual machine","author":"beguelin","year":"1991","journal-title":"Univ Tennessee Knoxville TN USA"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.92"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/11577188_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/289918.289920"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/971697.602266"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1145\/167962.165874","article-title":"Charm++: A portable concurrent object oriented system based on C++","volume":"28","author":"kale","year":"1993","journal-title":"ACM SIGPLAN Notices"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2287076.2287103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/42288.42291"},{"year":"0","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref17","first-page":"1","article-title":"Hierarchical work stealing on manycore clusters","author":"min","year":"0","journal-title":"Proc 5th Partitioned Global Address Space Programm Models"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.7"},{"key":"ref19","first-page":"442","article-title":"Improving performance via computational replication on a large-scale computational grid","volume":"3","author":"li","year":"0","journal-title":"Proc 3rd IEEE\/ACM Int Symp Cluster Comput Grid"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2","article-title":"SUMMA: Scalable universal matrix multiplication algorithm","volume":"9","author":"watts","year":"1997","journal-title":"Concurrency Practice and Experience"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465444"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.66"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45009-2_14"},{"key":"ref8","first-page":"1999","article-title":"The PageRank citation ranking: Bringing order to the Web","author":"page","year":"1999"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"ref2","first-page":"298","article-title":"StarPU-MPI: Task programming over clusters of machines enhanced with accelerators","author":"augonnet","year":"0","journal-title":"Proc 19th Eur Conf Recent Adv Message Passing Interf"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(96)00024-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2015.12"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0024718"},{"key":"ref22","first-page":"97","article-title":"Open MPI: Goals, concept, and design of a next generation MPI implementation","author":"gabriel","year":"0","journal-title":"The 11th European PVM\/MPI Users' Group Meeting"},{"key":"ref21","first-page":"48","article-title":"Locality aware work-stealing based scheduling in hybrid CPU-GPU clusters","author":"beri","year":"0","journal-title":"Proc Int Conf Parallel Distrib Process Techn Appl"},{"article-title":"Block LU factorization","year":"1995","author":"demmel","key":"ref24"},{"year":"2002","key":"ref23"},{"year":"0","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.681704"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7894348\/07588161.pdf?arnumber=7588161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:28Z","timestamp":1642003948000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7588161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,1]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2016.2616314","relation":{},"ISSN":["1045-9219"],"issn-type":[{"type":"print","value":"1045-9219"}],"subject":[],"published":{"date-parts":[[2017,5,1]]}}}