{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T15:38:54Z","timestamp":1729611534387,"version":"3.28.0"},"reference-count":9,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,11]]},"DOI":"10.1109\/dasip.2011.6136859","type":"proceedings-article","created":{"date-parts":[[2012,1,31]],"date-time":"2012-01-31T11:39:34Z","timestamp":1328009974000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["DFG implementation on multi GPU cluster with computation-communication overlap"],"prefix":"10.1109","author":[{"given":"Sylvain","family":"Huet","sequence":"first","affiliation":[]},{"given":"Vincent","family":"Boulos","sequence":"additional","affiliation":[]},{"given":"Vincent","family":"Fristot","sequence":"additional","affiliation":[]},{"given":"Luc","family":"Salvo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","volume":"abs 1005 2581","author":"karimi","year":"2010","journal-title":"A Performance Comparison of CUDA and OpenCL"},{"key":"ref3","article-title":"StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines","author":"augonnet","year":"2010","journal-title":"Research Report RR-7240 INRIA"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/S1007-0214(10)70002-X","article-title":"Iterative reconstruction for transmission tomography on gpu using nvidia cuda","volume":"15","author":"vintache","year":"2010","journal-title":"Tsinghua Science & Technology"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7056.001.0001","author":"gropp","year":"1999","journal-title":"Using MPI (2nd ed ) Portable Parallel Programming with the Message-Passing Interface"},{"journal-title":"NVIDIA CUDA C Programming Guide 3 2","year":"0","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2009.5193014"},{"key":"ref2","article-title":"Hmpp: A hybrid multi-core parallel programming environment","author":"dolbeau","year":"2007","journal-title":"Workshop on General Purpose Processing on Graphics Processing Units"},{"journal-title":"CUDA Occupancy Calculator","year":"0","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513902"}],"event":{"name":"2011 Conference on Design and Architectures for Signal and Image Processing (DASIP)","start":{"date-parts":[[2011,11,2]]},"location":"Tampere, Finland","end":{"date-parts":[[2011,11,4]]}},"container-title":["Proceedings of the 2011 Conference on Design & Architectures for Signal & Image Processing (DASIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6111682\/6136840\/06136859.pdf?arnumber=6136859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T22:52:56Z","timestamp":1561243976000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6136859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,11]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/dasip.2011.6136859","relation":{},"subject":[],"published":{"date-parts":[[2011,11]]}}}