{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:12:46Z","timestamp":1774627966608,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","award":["102-101-0028"],"award-info":[{"award-number":["102-101-0028"]}],"id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"PSF","award":["102-101-0028"],"award-info":[{"award-number":["102-101-0028"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2015,7,1]]},"DOI":"10.1109\/tpds.2014.2329494","type":"journal-article","created":{"date-parts":[[2014,6,19]],"date-time":"2014-06-19T12:46:45Z","timestamp":1403182005000},"page":"1789-1799","source":"Crossref","is-referenced-by-count":10,"title":["A Code Generation Framework for Targeting Optimized Library Calls for Multiple Platforms"],"prefix":"10.1109","volume":"26","author":[{"given":"Wen Jun","family":"Tan","sequence":"first","affiliation":[]},{"given":"Wai Teng","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Rick Siow Mong","family":"Goh","sequence":"additional","affiliation":[]},{"given":"Stephen John","family":"Turner","sequence":"additional","affiliation":[]},{"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","author":"aho","year":"2006","journal-title":"Compilers Principles Techniques and Tools"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407931"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-006-0012-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/109625.109631"},{"key":"ref35","year":"0","journal-title":"Nvidia CUBLAS Reference Manual"},{"key":"ref34","year":"0","journal-title":"Intel Math Kernel Library Reference Manual"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref11","first-page":"859","article-title":"OpenACC: First experiences with real-world applications","author":"wienke","year":"2012","journal-title":"Proc 18th Int Conf Parallel Process"},{"key":"ref12","article-title":"HMPP: A hybrid multicore parallel programming environment","author":"dolbeau","year":"2007","journal-title":"Proc Workshop General Purpose Process Graph Process Units"},{"key":"ref13","year":"0"},{"key":"ref14","year":"0"},{"key":"ref15","year":"0"},{"key":"ref16","year":"0"},{"key":"ref17","year":"0"},{"key":"ref18","year":"0"},{"key":"ref19","year":"0"},{"key":"ref4","first-page":"637","article-title":"Fast fluid dynamics simulation on the GPU","volume":"1","year":"2004","journal-title":"GPU Gems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38718-0_34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-52980-0.00010-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654119"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-37959-8","author":"tsutsui","year":"2013","journal-title":"Massively Parallel Evolutionary Computation on GPGPUs"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_20"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/180\/1\/012037"},{"key":"ref8","first-page":"298","article-title":"Intel threading building blocks","volume":"23","author":"pheatt","year":"2008","journal-title":"J Comput Sci Colleges"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/99.660313"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","article-title":"A survey of general-purpose computation on graphics hardware","volume":"26","year":"2007","journal-title":"Comput Graph Forum"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1365490.1365500"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2007.13"},{"key":"ref20","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1542476.1542481"},{"key":"ref21","year":"0"},{"key":"ref24","first-page":"35","article-title":"A heterogeneous parallel framework for domain-specific languages","author":"brown","year":"2012","journal-title":"Proc Int Conf Parallel Archit Compilation Tech"},{"key":"ref23","first-page":"232","article-title":"SPIRAL: Code generation for DSP transforms","volume":"93","author":"p\u00fcschel","year":"2005","journal-title":"Proc IEEE Special Issue Program Generation Optim Adaptation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/567806.567807"},{"key":"ref25","article-title":"BLIS: A framework for rapidly instantiating BLAS functionality","author":"van zee","year":"0","journal-title":"ACM Trans Math Softw"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7121064\/06827957.pdf?arnumber=6827957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:55Z","timestamp":1641987655000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6827957\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,1]]},"references-count":35,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2014.2329494","relation":{},"ISSN":["1045-9219"],"issn-type":[{"value":"1045-9219","type":"print"}],"subject":[],"published":{"date-parts":[[2015,7,1]]}}}