{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:07:54Z","timestamp":1729649274597,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,5]]},"DOI":"10.1109\/ipdpsw.2012.227","type":"proceedings-article","created":{"date-parts":[[2012,8,22]],"date-time":"2012-08-22T12:03:11Z","timestamp":1345636991000},"page":"1838-1847","source":"Crossref","is-referenced-by-count":11,"title":["Efficient Intranode Communication in GPU-Accelerated Systems"],"prefix":"10.1109","author":[{"given":"Feng","family":"Ji","sequence":"first","affiliation":[]},{"given":"Ashwin M.","family":"Aji","sequence":"additional","affiliation":[]},{"given":"James","family":"Dinan","sequence":"additional","affiliation":[]},{"given":"Darius","family":"Buntinas","sequence":"additional","affiliation":[]},{"given":"Pavan","family":"Balaji","sequence":"additional","affiliation":[]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Xiaosong","family":"Ma","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"NVIDIA GPUDirect","year":"0","key":"17"},{"journal-title":"NVIDIA CUDA Toolkit 4 1 Release Candidate 2","year":"0","key":"18"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.42"},{"key":"16","first-page":"353","article-title":"Open MPI: Goals, concept, and design of a next generation MPI implementation","volume":"3241","author":"gabriel","year":"2004","journal-title":"Lecture Notes in Computer Science"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1145\/2377978.2377981"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.67"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2011.83"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"journal-title":"NVIDIA CUDA C Programming Guide Version 4 0","year":"2011","key":"3"},{"journal-title":"Message Passing Interface Forum 2009","article-title":"MPI: A Message-Passing Interface Standard Version 2.2","year":"0","key":"2"},{"year":"0","key":"1"},{"key":"10","first-page":"23","article-title":"Lmbench: Portable tools for performance analysis","author":"mcvoy","year":"1996","journal-title":"Proceedings of the 1996 Annual Conference on USENIX Annual Technical Conference"},{"journal-title":"OpenCL 1 2","year":"0","key":"7"},{"journal-title":"OSU Micro-benchmarks 3 5","year":"2011","key":"6"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0171-3"},{"key":"4","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1007\/11846802_19","article-title":"Implementation and shared-memory evaluation of MPICH2 over the Nemesis communication subsystem","volume":"4192","author":"buntinas","year":"2006","journal-title":"Lecture Notes in Computer Science"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2006.31"},{"journal-title":"CUDA SDK Version 4 0","year":"2011","key":"8"}],"event":{"name":"2012 26th IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","start":{"date-parts":[[2012,5,21]]},"location":"Shanghai, China","end":{"date-parts":[[2012,5,25]]}},"container-title":["2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6269389\/6270391\/06270862.pdf?arnumber=6270862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T19:10:04Z","timestamp":1497985804000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6270862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,5]]},"references-count":18,"URL":"http:\/\/dx.doi.org\/10.1109\/ipdpsw.2012.227","relation":{},"subject":[],"published":{"date-parts":[[2012,5]]}}}
