{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T10:21:26Z","timestamp":1790936486441,"version":"4.1.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1109\/iscas.2010.5537722","type":"proceedings-article","created":{"date-parts":[[2010,8,9]],"date-time":"2010-08-09T18:13:20Z","timestamp":1281377600000},"page":"3801-3804","source":"Crossref","is-referenced-by-count":21,"title":["To GPU synchronize or not GPU synchronize?"],"prefix":"10.1109","author":[{"family":"Wu-chun Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Shucai Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","year":"2009","journal-title":"NVIDIA CUDA Programming Guide-2 2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(81)90087-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161066"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161065"},{"key":"ref15","first-page":"25","author":"volkov","year":"2006","journal-title":"Fitting FFT onto the G80 architecture"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2009.110"},{"key":"ref17","article-title":"Inter-Block GPU Communication via Fast Barrier Synchronization","author":"xiao","year":"2010","journal-title":"Proc of the IEEE International Parallel and Distributed Processing Symposium (to appear)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5213922"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/165231.165265"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77220-0_21"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407897"},{"key":"ref8","year":"2009","journal-title":"OpenCL Parallel Computing for Heterogeneous Devices"},{"key":"ref7","article-title":"On Implementing Graph Cuts on CUDA","author":"hussein","year":"2007","journal-title":"First Workshop on General Purpose Processing on Graphics Processing Units"},{"key":"ref2","year":"2009","journal-title":"Stream Computing User Guide"},{"key":"ref1","author":"alemany","year":"1992","journal-title":"Proc of the 11th ACM Symp on Principles of Distributed Computing"},{"key":"ref9","author":"lang","year":"1997","journal-title":"Bitonic Sort"}],"event":{"name":"2010 IEEE International Symposium on Circuits and Systems. ISCAS 2010","location":"Paris","start":{"date-parts":[[2010,5,30]]},"end":{"date-parts":[[2010,6,2]]}},"container-title":["Proceedings of 2010 IEEE International Symposium on Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5512009\/5536941\/05537722.pdf?arnumber=5537722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,19]],"date-time":"2017-03-19T02:00:31Z","timestamp":1489888831000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5537722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iscas.2010.5537722","relation":{},"subject":[],"published":{"date-parts":[[2010,5]]}}}