{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:31:16Z","timestamp":1782959476418,"version":"3.54.5"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2011,4,12]],"date-time":"2011-04-12T00:00:00Z","timestamp":1302566400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comput Sci Res Dev"],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1007\/s00450-011-0171-3","type":"journal-article","created":{"date-parts":[[2011,4,21]],"date-time":"2011-04-21T09:49:15Z","timestamp":1303379355000},"page":"257-266","source":"Crossref","is-referenced-by-count":104,"title":["MVAPICH2-GPU: optimized GPU to GPU communication for InfiniBand clusters"],"prefix":"10.1007","volume":"26","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sreeram","family":"Potluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashish Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayantan","family":"Sur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhabaleswar K.","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2011,4,12]]},"reference":[{"key":"171_CR1","unstructured":"TOP500 Supercomputing Sites. http:\/\/www.top500.org\/"},{"key":"171_CR2","volume-title":"Proceedings of the 2010 IEEE international conference on cluster computing (Cluster\u201910)","author":"W Ma","year":"2010","unstructured":"Ma W, Krishnamoorthy S, Villa O, Kowalski K (2010) Acceleration of streamed tensor contraction expressions on GPGPU-based clusters. In: Proceedings of the 2010 IEEE international conference on cluster computing (Cluster\u201910)"},{"key":"171_CR3","volume-title":"Proceedings of the 48th AIAA aerospace sciences meeting","author":"DA Jacobsen","year":"2010","unstructured":"Jacobsen DA, Thibault JC, Senocak I (2010) An MPI-CUDA implementation for massively parallel incompressible flow computations on multi-GPU clusters. In: Proceedings of the 48th AIAA aerospace sciences meeting"},{"key":"171_CR4","volume-title":"Proceedings of the 24th IEEE international parallel and distributed processing symposium (IPDPS\u201910)","author":"EH Phillips","year":"2010","unstructured":"Phillips EH, Fatica M (2010) Implementing the Himeno benchmark with CUDA on GPU clusters. In: Proceedings of the 24th IEEE international parallel and distributed processing symposium (IPDPS\u201910)"},{"key":"171_CR5","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1145\/1693453.1693471","volume-title":"Proceedings of the 15th ACM SIGPLAN symposium on principles and practice of parallel programming (PPoPP\u201910)","author":"JW Choi","year":"2010","unstructured":"Choi JW, Singh A, Vuduc RW (2010) Model-driven autotuning of sparse matrix-vector multiply on GPUs. In: Proceedings of the 15th ACM SIGPLAN symposium on principles and practice of parallel programming (PPoPP\u201910), pp 115\u2013126"},{"issue":"2","key":"171_CR6","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1111\/j.1467-8659.2008.01131.x","volume":"27","author":"Z Fan","year":"2008","unstructured":"Fan Z, Qiu F, Kaufman AE (2008) Zippy: a framework for computation and visualization on a GPU cluster. Comput. Graph. Forum 27(2):341\u2013350","journal-title":"Comput. Graph. Forum"},{"key":"171_CR7","volume-title":"Proceedings of the 23th IEEE international parallel and distributed processing symposium (IPDPS\u201909)","author":"JA Stuart","year":"2009","unstructured":"Stuart JA, Owens JD (2009) Message passing on data-parallel architectures. In: Proceedings of the 23th IEEE international parallel and distributed processing symposium (IPDPS\u201909)"},{"key":"171_CR8","unstructured":"MVAPICH2: High performance MPI over InfiniBand\/10GigE\/iWARP and RoCE. http:\/\/mvapich.cse.ohio-state.edu\/"},{"key":"171_CR9","unstructured":"InfiniBand Trade Association. http:\/\/www.infinibandta.com"},{"key":"171_CR10","unstructured":"NVIDIA: NVIDIA CUDA compute unified device architecture. http:\/\/developer.download.nvidia.com\/compute\/cuda\/2_0\/docs\/CudaReferenceManual_2.0.pdf"},{"key":"171_CR11","unstructured":"Mellanox: NVIDIA GPUDirect technology\u2014accelerating GPU-based systems. http:\/\/www.mellanox.com\/pdf\/whitepapers\/TB_GPU_Direct.pdf"},{"key":"171_CR12","unstructured":"OSU Micro Benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"171_CR13","unstructured":"AMD: AMD fusion family of APUs: enabling a superior, immersive PC experience. http:\/\/sites.amd.com\/us\/Documents\/48423B_fusion_whitepaper_WEB.pdf"}],"container-title":["Computer Science - Research and Development"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-011-0171-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00450-011-0171-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-011-0171-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T09:32:47Z","timestamp":1559122367000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00450-011-0171-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4,12]]},"references-count":13,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2011,6]]}},"alternative-id":["171"],"URL":"https:\/\/doi.org\/10.1007\/s00450-011-0171-3","relation":{},"ISSN":["1865-2034","1865-2042"],"issn-type":[{"value":"1865-2034","type":"print"},{"value":"1865-2042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,4,12]]}}}