{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T21:06:55Z","timestamp":1761512815313,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,4]]},"DOI":"10.1109\/ipdpsw.2010.5470833","type":"proceedings-article","created":{"date-parts":[[2010,5,28]],"date-time":"2010-05-28T18:25:42Z","timestamp":1275071142000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Parallel external sorting for CUDA-enabled GPUs with load balancing and low transfer overhead"],"prefix":"10.1109","author":[{"given":"Hagen","family":"Peters","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ole","family":"Schulz-Hildebrandt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norbert","family":"Luttenberger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2006.1639284"},{"key":"ref11","article-title":"Parallel prefix sum (scan) with cuda","author":"harris","year":"2007","journal-title":"GPU Gems 3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362684"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/360128.360145"},{"journal-title":"1 introduction parallel sorting on gpu clus-ters","year":"2007","author":"kerwin","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1058129.1058146"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(93)90019-H"},{"key":"ref17","article-title":"Fast in-place sorting with cuda based on bitonic sort","author":"peters","year":"2009","journal-title":"In To appear in PPAM09 Proceedings of the International Conference on Parallel Processing and Applied Mathematics"},{"key":"ref18","first-page":"41","article-title":"Photon mapping on programmable graphics hardware","author":"purcell","year":"2003","journal-title":"HWWS '03 Proceedings of the ACM SIGGRAPH\/EUROGRAPHICS conference on Graphics hardware"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/978-3-642-03095-6_28","article-title":"A fast and flexible sorting algorithm with cuda","author":"chen","year":"2009","journal-title":"ICA3PP '09 Proceedings of the 9th International Conference on Algorithms and Architectures for Parallel Processing"},{"key":"ref3","first-page":"246","article-title":"A practical quicksort algorithm for graphics processors","author":"cederman","year":"2008","journal-title":"ESA '08 Proceedings of the 16th annual European Symposium on Algorithms"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/361020.361216"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454171"},{"key":"ref8","article-title":"A cache-efficient sorting algorithm for database and data mining computations using graphics processors","author":"govindaraju","year":"2005","journal-title":"Technical report University of North Carolina at Chapel Hill"},{"key":"ref7","first-page":"325","article-title":"Gputerasort: high performance graphics co-processor sorting for large database man-agement","year":"2006","journal-title":"SIGMOD '06 Proceedings of the 2006 ACM SIGMOD international conference on Management of data"},{"key":"ref2","article-title":"Sorting networks and their applications","author":"batcher","year":"1967","journal-title":"AFIPS Spring Joint Comput Conf"},{"year":"0","key":"ref1"},{"key":"ref9","article-title":"Broad-phase collision detection with cuda","author":"grand","year":"2007","journal-title":"GPU Gems 3"},{"key":"ref20","first-page":"97","article-title":"Scan primitives for gpu computing","author":"sengupta","year":"2007","journal-title":"GH '07 Proceedings of the 22nd ACM SIGGRAPH\/EUROGRAPHICS Symposium on Graphics Hardware"},{"key":"ref22","first-page":"1381","volume":"68","author":"sintorn","year":"2008","journal-title":"Fast parallel gpu-sorting using a hybrid algorithm"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/0743-7315(92)90075-X","article-title":"Parallel sorting by regular sampling","volume":"14","author":"shi","year":"1992","journal-title":"J Parallel Distrib Comput"}],"event":{"name":"Distributed Processing, Workshops and Phd Forum (IPDPSW)","start":{"date-parts":[[2010,4,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2010,4,23]]}},"container-title":["2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5465895\/5470678\/05470833.pdf?arnumber=5470833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T08:48:44Z","timestamp":1497862124000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5470833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ipdpsw.2010.5470833","relation":{},"subject":[],"published":{"date-parts":[[2010,4]]}}}