{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T08:48:57Z","timestamp":1672562937038},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2009,5,6]],"date-time":"2009-05-06T00:00:00Z","timestamp":1241568000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Sci. Res. Dev."],"published-print":{"date-parts":[[2009,6]]},"DOI":"10.1007\/s00450-009-0090-8","type":"journal-article","created":{"date-parts":[[2009,5,5]],"date-time":"2009-05-05T02:28:07Z","timestamp":1241490487000},"page":"133-142","source":"Crossref","is-referenced-by-count":7,"title":["ProOnE: a\u00a0general-purpose protocol onload engine for multi- and many-core architectures"],"prefix":"10.1007","volume":"23","author":[{"given":"P.","family":"Lai","sequence":"first","affiliation":[]},{"given":"P.","family":"Balaji","sequence":"additional","affiliation":[]},{"given":"R.","family":"Thakur","sequence":"additional","affiliation":[]},{"given":"D. K.","family":"Panda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,5,6]]},"reference":[{"key":"90_CR1","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Virtual_Interface_Architecture"},{"key":"90_CR2","unstructured":"http:\/\/www.myri.com\/myrinet\/overview\/"},{"key":"90_CR3","unstructured":"www.quadrics.com\/"},{"key":"90_CR4","unstructured":"http:\/\/www.intel.com\/products\/processor\/core2XE\/"},{"key":"90_CR5","unstructured":"http:\/\/www.sun.com\/processors\/niagara\/"},{"key":"90_CR6","unstructured":"Chelsio TOE. http:\/\/www.chelsio.com\/"},{"key":"90_CR7","unstructured":"Giganet clan. http:\/\/www.emulex.com\/"},{"key":"90_CR8","unstructured":"InfiniBand Trade Association. http:\/\/www.infinibandta.com"},{"key":"90_CR9","unstructured":"Jacobi Method. http:\/\/en.wikipedia.org\/wiki\/Jacobi_method"},{"key":"90_CR10","unstructured":"MPICH2. http:\/\/www.mcs.anl.gov\/research\/projects\/mpich2\/"},{"key":"90_CR11","unstructured":"OpenMP. http:\/\/openmp.org\/wp\/"},{"key":"90_CR12","unstructured":"Top 500 SuperComputer Sites. http:\/\/www.top500.org\/"},{"key":"90_CR13","unstructured":"Amerson G, Apon A (2004) Implementation and design analysis of a network messaging module using virtual interface architecture. In: International Conference on Cluster Computing"},{"key":"90_CR14","unstructured":"Regnier G, Minturn D, McAlpine G, Saletore V, Foong A (2003) ETA: experience with an Intel Xeon processor as a packet processing engin. In: Proceedings of the 11th Symposium on High Performance Interconnects (HOTI\u201903)"},{"key":"90_CR15","doi-asserted-by":"crossref","DOI":"10.1145\/1006209.1006251","volume-title":"An analysis of the impact of MPI overlap and independent progress","author":"R Brightwell","year":"2004","unstructured":"Brightwell R, Underwood KD (2004) An analysis of the impact of MPI overlap and independent progress. In: Proceedings of the 18th annual international conference on Supercomputing, March 2004"},{"key":"90_CR16","doi-asserted-by":"crossref","unstructured":"Chai L, Hartono A, Panda DK (2006) Designing high performance and scalable MPI intra-node communication support for clusters. In: The IEEE International Conference on Cluster Computing","DOI":"10.1109\/CLUSTR.2006.311850"},{"key":"90_CR17","unstructured":"MPI Forum (1993) MPI: A Message Passing Interface"},{"key":"90_CR18","unstructured":"Gropp W, Lusk E, Doss N, Skjellum A. A high-performance, portable implementation of the MPI. Technical report, Argonne National Laboratory and Mississippi State University"},{"key":"90_CR19","doi-asserted-by":"crossref","unstructured":"Jin H-W, Sur S, Chai L, Panda DK (2007) Lightweight Kernel-Level Primitives for High-performance MPI Intra-Node Communication over Multi-Core Systems. In: IEEE International Conference on Cluster Computing (poster presentation)","DOI":"10.1109\/CLUSTR.2007.4629263"},{"key":"90_CR20","doi-asserted-by":"crossref","unstructured":"Kumar R, Mamidala AR, Koop MJ, Santhanaraman G, Panda DK (2008) Lock-free asynchronous rendezvous design for MPI Point-to-point communication. In: EuroPVM \u201908","DOI":"10.1007\/978-3-540-87475-1_27"},{"key":"90_CR21","unstructured":"Majumder S, Rixner S, Pai VS (2004) An event-driven architecture for mpi libraries. In: Computer Science Institute Symposium"},{"key":"90_CR22","doi-asserted-by":"crossref","unstructured":"Ortiz A, Ortega J, Daz AF, Prieto A (2008) Comparison of onloading and offloading strategies to improve network interfaces. In PDP. IEEE Computer Society, 2008.","DOI":"10.1109\/PDP.2008.20"},{"key":"90_CR23","doi-asserted-by":"crossref","unstructured":"Regnier G, Makineni S, Illikkal R, Minturn D, Huggahalli R, Newell D, Cline L, Foong A. TCP onloading for data center servers. IEEE Comput 37(11):48\u201358","DOI":"10.1109\/MC.2004.223"},{"key":"90_CR24","doi-asserted-by":"crossref","unstructured":"Sancho JC, Barker KJ, Kerbyson DJ, Davis K (2006) Quantifying the potential benefit of overlapping communication and computation in large-scale scientific applications. In: ACM\/IEEESC 2006 Conference (SC\u201906)","DOI":"10.1109\/SC.2006.51"},{"key":"90_CR25","doi-asserted-by":"crossref","unstructured":"Sancho JC, Kerbyson DJ, Barker KJ (2007) Efficient offloading of collective communications in large-scale systems. In: IEEE International Conference on Cluster Computing","DOI":"10.1109\/CLUSTR.2007.4629229"},{"key":"90_CR26","unstructured":"Sandia National Laboratories. Sandia MPI Micro-Benchmark Suite. http:\/\/www.cs.sandia.gov\/smb\/"},{"key":"90_CR27","doi-asserted-by":"crossref","unstructured":"Shivam P, Chase JS (2003) On the elusive benefits of protocol offload. In: SIGCOMM\u201903 Workshop on NICELI","DOI":"10.1145\/944747.944750"},{"key":"90_CR28","doi-asserted-by":"crossref","unstructured":"Sur S, Jin H-W, Chai L, Panda DK (2006) RDMA read based rendezvous protocol for MPI over InfiniBand: design alternatives and benefits. In: Symposium on PPOPP, March 2006","DOI":"10.1145\/1122971.1122978"},{"key":"90_CR29","doi-asserted-by":"crossref","unstructured":"Trahay F, Brunet E, Denis A, Namyst R (2008) A multithreaded communication engine for multicore architectures. In: International Parallel and Distributed Processing (IPDPS)","DOI":"10.1109\/IPDPS.2008.4536139"},{"key":"90_CR30","doi-asserted-by":"crossref","unstructured":"Vaidyanathan K, Lai P, Narravula S, Panda DK (2008) Optimized distributed data sharing substrate in multi-core commodity clusters: A comprehensive study with applications. In: International Symposium on Cluster Computing and the Grid (CCGrid), May 2008","DOI":"10.1109\/CCGRID.2008.116"}],"container-title":["Computer Science - Research and Development"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-009-0090-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00450-009-0090-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-009-0090-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T09:32:45Z","timestamp":1559122365000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00450-009-0090-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,5,6]]},"references-count":30,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2009,6]]}},"alternative-id":["90"],"URL":"https:\/\/doi.org\/10.1007\/s00450-009-0090-8","relation":{},"ISSN":["1865-2034","1865-2042"],"issn-type":[{"value":"1865-2034","type":"print"},{"value":"1865-2042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,5,6]]}}}