{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T02:31:17Z","timestamp":1782959477012,"version":"3.54.5"},"publisher-location":"Berlin, Heidelberg","reference-count":18,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642335174","type":"print"},{"value":"9783642335181","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33518-1_16","type":"book-chapter","created":{"date-parts":[[2012,9,8]],"date-time":"2012-09-08T08:17:23Z","timestamp":1347092243000},"page":"110-120","source":"Crossref","is-referenced-by-count":47,"title":["OMB-GPU: A Micro-Benchmark Suite for Evaluating MPI Libraries on GPU Clusters"],"prefix":"10.1007","author":[{"given":"D.","family":"Bureddy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.","family":"Venkatesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Potluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D. K.","family":"Panda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"16_CR1","unstructured":"Intel MPI Benchmark, \n                    \n                      http:\/\/www.intel.com\/cd\/software\/products\/"},{"key":"16_CR2","unstructured":"Jacket GBENCH, \n                    \n                      http:\/\/www.accelereyes.com\/gbench"},{"key":"16_CR3","unstructured":"NAS Parallel Benchmarks, \n                    \n                      http:\/\/www.nas.nasa.gov"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Che, S., Sheaffer, J.W., Boyer, M., Szafaryn, L.G., Wang, L., Skadron, K.: A Characterization of the Rodinia Benchmark Suite with Comparison to Contemporary CMP Workloads. In: Proceedings of the 2009 IEEE International Symposium on Workload Characterization, IISWC 2009 (2009)","DOI":"10.1109\/IISWC.2010.5650274"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Danalis, A., Marin, G., McCurdy, C., Meredith, J.S., Roth, P.C., Spafford, K., Tipparaju, V., Vetter, J.S.: The Scalable HeterOgeneous Computing (SHOC) Benchmark Suite. In: Proceedings of the 3rd Workshop on General Purpose Processing on Graphics Processing Units, GPGPU 2010 (2010)","DOI":"10.1145\/1735688.1735702"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Ji, F., Aji, A.M., Dinan, J., Buntinas, D., Balaji, P., Feng, W., Ma, X.: Efficient Intranode Communication in GPU-Accelerated Systems. In: Proceedings of AsHES, in conjunction with IPDPS 2012 (2012)","DOI":"10.1109\/IPDPSW.2012.227"},{"key":"16_CR7","unstructured":"Argonne National Laboratory: MPICH2: High-performance and Widely Portable MPI, \n                    \n                      http:\/\/www.mcs.anl.gov\/research\/projects\/mpich2\/"},{"key":"16_CR8","unstructured":"Network-Based Computing Laboratory: MVAPICH: MPI over InfiniBand and 10GigE\/iWARP, \n                    \n                      http:\/\/mvapich.cse.ohio-state.edu\/"},{"key":"16_CR9","unstructured":"Open MPI: Open Source High Performance Computing, \n                    \n                      http:\/\/www.open-mpi.org"},{"key":"16_CR10","unstructured":"OSU Microbenchmarks, \n                    \n                      http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"16_CR11","unstructured":"Parboil Benchmarks, \n                    \n                      http:\/\/impact.crhc.illinois.edu\/parboil.aspx"},{"key":"16_CR12","unstructured":"Portable Hardware Locality (hwloc), \n                    \n                      http:\/\/www.open-mpi.org\/projects\/hwloc\/"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Potluri, S., Wang, H., Bureddy, D., Singh, A.K., Rosales, C., Panda, D.K.: Optimizaing MPI Communication on Multi-GPU Systems using CUDA Inter-Process Communication. In: Proceedings of the AsHES, in conjunction with IPDPS 2012 (2012)","DOI":"10.1109\/IPDPSW.2012.228"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Singh, A.K., Potluri, S., Wang, H., Kandalla, K., Sur, S., Panda, D.K.: MPI Alltoall Personalized Exchange on GPGPU Clusters: Design Alternatives and Benefits. In: Proceedings of the Workshop on Parallel Programming on Accelerator Clusters (PPAC), in conjunction with Cluster 2011 (2011)","DOI":"10.1109\/CLUSTER.2011.67"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Spafford, K., Meredith, J.S., Vetter, J.S.: Quantifying NUMA and Contention Effects in Multi-GPU systems. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, GPGPU 2011 (2011)","DOI":"10.1145\/1964179.1964194"},{"key":"16_CR16","unstructured":"SPEC MPI 2007, \n                    \n                      http:\/\/www.spec.org\/mpi\/"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Wang, H., Potluri, S., Luo, M., Singh, A.K., Ouyang, X., Sur, S., Panda, D.K.: Optimized Non-contiguous MPI Datatype Communication for GPU Clusters: Design, Implementation and Evaluation with MVAPICH2. In: Proceedings of Cluster 2011 (2011)","DOI":"10.1109\/CLUSTER.2011.42"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Potluri, S., Luo, M., Singh, A.K., Sur, S., Panda, D.K.: MVAPICH2-GPU: Optimized GPU to GPU Communication for InfiniBand Clusters. In: Proceedings of the 2011 International Supercomputing Conference, ISC 2011 (2011)","DOI":"10.1007\/s00450-011-0171-3"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in the Message Passing Interface"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33518-1_16.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T08:14:08Z","timestamp":1620116048000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33518-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642335174","9783642335181"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33518-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}