{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:06:33Z","timestamp":1791320793898,"version":"4.3.1"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/hpca.2016.7446058","type":"proceedings-article","created":{"date-parts":[[2016,4,4]],"date-time":"2016-04-04T22:03:56Z","timestamp":1459807436000},"page":"114-125","source":"Crossref","is-referenced-by-count":62,"title":["A performance analysis framework for optimizing OpenCL applications on FPGAs"],"prefix":"10.1109","author":[{"given":"Zeke","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunning","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2015.7293941"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304624"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1661438.1661443"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2012.6339272"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/428078"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-009-0387-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536216"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/2735496.2735497"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2007.79"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537736"},{"key":"ref4","article-title":"clspmv: A cross-platform opencl spmv framework on gpus","author":"bor-","year":"2012","journal-title":"ACM International Conference on Supercomputing (ICS)"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1145\/1345206.1345220","article-title":"Optimization principles and application performance evaluation of a multithreaded gpu using cuda","author":"ryoo","year":"2008","journal-title":"Principles Practice of Parallel Programming"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145819"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1950413.1950423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2013.6509612"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2012.6339171"},{"key":"ref2","author":"altera","year":"2014","journal-title":"Altera SDK for OpenCL Optimization Guide"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2287076.2287109"},{"key":"ref1","article-title":"Implementing fpga design with the opencl standard","author":"altera","year":"0","journal-title":"Altera Whitepaper"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2003.1204375"},{"key":"ref21","article-title":"Dynamic critical-path scheduling: an effective technique for allocating task graphs to multiprocessors","author":"kwok","year":"1996","journal-title":"IEEE Transactions on Parallel and Distributed Systems (TPDS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2068716.2068722"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853195"},{"key":"ref25","article-title":"Performance and area modeling of complete fpga designs in the presence of loop transformations","author":"park","year":"2004","journal-title":"IEEE Transactions on Computers (TC)"}],"event":{"name":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Barcelona, Spain","start":{"date-parts":[[2016,3,12]]},"end":{"date-parts":[[2016,3,16]]}},"container-title":["2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7440961\/7446041\/7446058.pdf?arnumber=7446058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T13:27:24Z","timestamp":1692278844000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7446058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/hpca.2016.7446058","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}