{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T13:52:38Z","timestamp":1790517158482,"version":"4.1.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/hipc.2014.7116873","type":"proceedings-article","created":{"date-parts":[[2015,6,10]],"date-time":"2015-06-10T19:32:46Z","timestamp":1433964766000},"page":"1-10","source":"Crossref","is-referenced-by-count":36,"title":["Designing efficient small message transfer mechanism for inter-node MPI communication on InfiniBand GPU clusters"],"prefix":"10.1109","author":[{"given":"Rong","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sreeram","family":"Potluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khaled","family":"Hamidouche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Perkins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhe","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Rossetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhabaleswar K. D K","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Efficient Inter-node MPI Communication using GPUDirect RDMA for InfiniBand Clusters with NVIDIA GPUs","author":"potluri","year":"2012","journal-title":"Proceeding of International Conference on Parallel Processing (ICPP'12)"},{"key":"ref11","year":"0","journal-title":"Infini Band"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.128"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-33518-1_16","article-title":"OMB-GPU: A Micro-benchmark Suite for Evaluating MPI Libraries on GPU Clusters","author":"bureddy","year":"2012","journal-title":"Proceedings of the 19th European conference on Recent Advances in the Message Passing Interface"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.67"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2011.9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2008.01.047"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2159430.2159433"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2212736.2212744"},{"key":"ref19","article-title":"Multi-Threaded UPC Runtime for GPU to GPU communication over InfiniBand","author":"luo","year":"2012","journal-title":"The 6th Conference on Partitioned Global Address Space Programming Models 2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2013.6702619"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2159430.2159437"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2012.228"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00450-011-0171-3"},{"key":"ref8","year":"0","journal-title":"MVAPICH2 MPI over InfiniBand 10GigE\/iWARP and RoCE"},{"key":"ref7","article-title":"GPUDirect","year":"0"},{"key":"ref2","year":"0"},{"key":"ref9","article-title":"OpenMPI: Open Source High Performance Computing","year":"0"},{"key":"ref1","year":"0","journal-title":"Top500"},{"key":"ref20","article-title":"Message Passing for GPGPU Clusters: Cud-aMPI","author":"lawlor","year":"2009","journal-title":"Proceeding of Cluster Computing and Workshops (CLUSTER '09)"},{"key":"ref22","article-title":"Processing MPI Derived Datatypes on Noncontiguous GPU-Resident Data","author":"jenkins","year":"2013","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"ref21","article-title":"GPU-Aware MPI on RDMA-Enabled Clusters: Design, Implementation and Evaluation","author":"wang","year":"2013","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161065"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2014.31"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2012.92"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2014.111"}],"event":{"name":"2014 21st International Conference on High Performance Computing (HiPC)","location":"Goa, India","start":{"date-parts":[[2014,12,17]]},"end":{"date-parts":[[2014,12,20]]}},"container-title":["2014 21st International Conference on High Performance Computing (HiPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7113430\/7116705\/07116873.pdf?arnumber=7116873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T13:23:31Z","timestamp":1498224211000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7116873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/hipc.2014.7116873","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}