{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:18:09Z","timestamp":1740133089479,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2013R1A3A2003664","2016M3C4A7952587","21A20151113068"],"award-info":[{"award-number":["2013R1A3A2003664","2016M3C4A7952587","21A20151113068"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2018,2,1]]},"DOI":"10.1109\/tpds.2017.2755657","type":"journal-article","created":{"date-parts":[[2017,9,22]],"date-time":"2017-09-22T18:14:05Z","timestamp":1506104045000},"page":"283-296","source":"Crossref","is-referenced-by-count":9,"title":["An Auto-Tuner for OpenCL Work-Group Size on GPUs"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9897-2769","authenticated-orcid":false,"given":"Thanh Tuan","family":"Dao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4638-8170","authenticated-orcid":false,"given":"Jaejin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"article-title":"Parboil: A revised benchmark\n suite for scientific and commercial throughput computing","year":"2012","author":"stratton","key":"ref32"},{"key":"ref31","first-page":"387","article-title":"Automatic OpenCL work-group size selection for multicore\n CPUs","author":"seo","year":"2013","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2011.6114174"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1809028.1806606"},{"key":"ref10","first-page":"157","article-title":"Neither more nor less:\n Optimizing thread-level parallelism for GPGPUs","author":"kay?ran","year":"2013","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.36"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1816038.1816021"},{"key":"ref13","first-page":"1","article-title":"A cross-input adaptive\n framework for GPU program optimizations","author":"liu","year":"2009","journal-title":"Proc Int Parallel Distrib Process Symp"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155664"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872411"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654090"},{"journal-title":"NVIDIA OpenCL SDK Code Samples","year":"2017","key":"ref17"},{"journal-title":"PTX Parallel Thread Execution ISA Version 1 4","year":"2017","key":"ref18"},{"journal-title":"NVIDIA Compute Visual Profiler User Guide Version 04","year":"2017","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2813885.2737969"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"ref8","first-page":"185","article-title":"Automatic tuning matrix multiplication performance on graphics hardware","author":"jiang","year":"2005","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.59"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628092"},{"year":"2017","key":"ref20"},{"year":"2017","key":"ref22"},{"year":"2017","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2499368.2451162"},{"year":"2017","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750410"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8258926\/08048544.pdf?arnumber=8048544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:25:42Z","timestamp":1642004742000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8048544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,1]]},"references-count":35,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2017.2755657","relation":{},"ISSN":["1045-9219"],"issn-type":[{"type":"print","value":"1045-9219"}],"subject":[],"published":{"date-parts":[[2018,2,1]]}}}