{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:45:53Z","timestamp":1775231153183,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["201506270152"],"award-info":[{"award-number":["201506270152"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872393"],"award-info":[{"award-number":["61872393"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CCF-1657333"],"award-info":[{"award-number":["NSF-CCF-1657333"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CCF-1717754"],"award-info":[{"award-number":["NSF-CCF-1717754"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CNS-1717984"],"award-info":[{"award-number":["NSF-CNS-1717984"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-CCF-1750656"],"award-info":[{"award-number":["NSF-CCF-1750656"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2020,5,1]]},"DOI":"10.1109\/tpds.2019.2958343","type":"journal-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T20:57:26Z","timestamp":1579640246000},"page":"1089-1106","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Performance Estimation and Work-Group Size Pruning for OpenCL Kernels on GPUs"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4885-4959","authenticated-orcid":false,"given":"Xiebing","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehai","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654090"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2010.43"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.7873\/DATE.2015.0916"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2333526"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362674"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2005.10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2764908"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1145\/1854273.1854318","article-title":"Ocelot: A dynamic optimization framework for bulk-synchronous applications in heterogeneous systems","author":"diamos","year":"2010","journal-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2011.51"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD.2014.30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/NCA.2016.7778637"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830780"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/79173.79181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/S009753979427491"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/800133.804339"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.73"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079083"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8645000"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2014.7116897"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2755657"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2017.61"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2162131.2162136"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1555815.1555775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1837853.1693470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HIPC.2009.5433179"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2015.34"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2016.04.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3126557"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.53"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2494232.2465540"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC.2015.10"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557151"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.85"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23397-5_43"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3126546"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2988336.2988355"},{"key":"ref41","first-page":"157","article-title":"Neither more nor less: Optimizing thread-level parallelism for GPGPUs","author":"kay?ran","year":"2013","journal-title":"Proc Int l Conf Parallel Architectures and Compilation Techniques"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45306-7_9"},{"key":"ref43","first-page":"185","article-title":"LOOPUS: A tool for computing loop bounds for C programs","author":"sinn","year":"2010","journal-title":"Proc Workshop Invariant Gener"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/8965248\/8928962-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8965248\/08928962.pdf?arnumber=8928962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:40:37Z","timestamp":1651070437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8928962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,1]]},"references-count":50,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2019.2958343","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":[[2020,5,1]]}}}