{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:31:07Z","timestamp":1705350667207},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2013,5,9]],"date-time":"2013-05-09T00:00:00Z","timestamp":1368057600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s00607-013-0327-z","type":"journal-article","created":{"date-parts":[[2013,5,8]],"date-time":"2013-05-08T08:31:54Z","timestamp":1368001914000},"page":"263-278","source":"Crossref","is-referenced-by-count":7,"title":["Improving MPI communication overlap with collaborative polling"],"prefix":"10.1007","volume":"96","author":[{"given":"Sylvain","family":"Didelot","sequence":"first","affiliation":[]},{"given":"Patrick","family":"Carribault","sequence":"additional","affiliation":[]},{"given":"Marc","family":"P\u00e9rache","sequence":"additional","affiliation":[]},{"given":"William","family":"Jalby","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,5,9]]},"reference":[{"key":"327_CR1","unstructured":"Iii JBW, Bova SW (1999) Where\u2019s the overlap? An analysis of popular MPI implementations. Technical report (August 12 1999)"},{"key":"327_CR2","doi-asserted-by":"crossref","unstructured":"Brightwell R, Riesen R, Underwood KD (2005) Analyzing the impact of overlap, offload, and independent progress for message passing interface applications. IJHPCA","DOI":"10.1177\/1094342005054257"},{"key":"327_CR3","doi-asserted-by":"crossref","unstructured":"P\u00e9rache M, Carribault P, Jourdren H (2009) MPC-MPI: an MPI implementation reducing the overall memory consumption. In: PVM\/MPI","DOI":"10.1007\/978-3-642-03770-2_16"},{"key":"327_CR4","doi-asserted-by":"crossref","unstructured":"Bell C, Bonachea D, Nishtala R, Yelick KA (2006) Optimizing bandwidth limited problems using one-sided communication and overlap. In: IPDPS","DOI":"10.1109\/IPDPS.2006.1639320"},{"key":"327_CR5","doi-asserted-by":"crossref","unstructured":"Subotic V, Sancho JC, Labarta J, Valero M (2011) The impact of application\u2019s micro-imbalance on the communication-computation overlap. In: Parallel, distributed and network-based processing (PDP)","DOI":"10.1109\/PDP.2011.61"},{"key":"327_CR6","unstructured":"Thakur R, Gropp W (2007) Test suite for evaluating performance of MPI implementations that support $$\\text{ MPI }\\_\\text{ THREAD }\\_\\text{ MULTIPLE }$$ . In: PVM\/MPI. pp 46\u201355"},{"key":"327_CR7","doi-asserted-by":"crossref","unstructured":"Hager G, Jost G, Rabenseifner R (2009) Communication characteristics and hybrid MPI\/OpenMP parallel programming on clusters of multi-core SMP nodes. In: Proceedings of Cray User Group","DOI":"10.1109\/PDP.2009.43"},{"key":"327_CR8","doi-asserted-by":"crossref","unstructured":"Graham R, Poole S, Shamis P, Bloch G, Bloch N, Chapman H, Kagan M, Shahar A, Rabinovitz I, Shainer G (2010) Connectx-2 infiniband management queues: first investigation of the new support for network offloaded collective operations. In: International conference on cluster, cloud and grid computing (CCGRID)","DOI":"10.1109\/CCGRID.2010.9"},{"key":"327_CR9","doi-asserted-by":"crossref","unstructured":"Kamal H, Wagner A (2012) Added concurrency to improve MPI performance on multicore. In: ICPP, IEEE Computer Society, pp 229\u2013238","DOI":"10.1109\/ICPP.2012.15"},{"key":"327_CR10","doi-asserted-by":"crossref","unstructured":"Alm\u00e1si G, Bellofatto R, Brunheroto J, Ca\u015fcaval C, Casta\u00f1os JG, Crumley P, Erway CC, Lieber D, Martorell X, Moreira JE, Sahoo R, Sanomiya A, Ceze L, Strauss K (2003) An overview of the bluegene\/L system software organization. Parallel Process Lett","DOI":"10.1142\/S0129626403001513"},{"key":"327_CR11","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":"327_CR12","doi-asserted-by":"crossref","unstructured":"Sur S, Jin Hw, Chai L, Panda DK (2006) RDMA read based Rendezvous protocol for MPI over infiniBand: design alternatives and benefits. Alternatives","DOI":"10.1145\/1122971.1122978"},{"key":"327_CR13","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: PVM\/MPI","DOI":"10.1007\/978-3-540-87475-1_27"},{"key":"327_CR14","doi-asserted-by":"crossref","unstructured":"Hoefler T, Lumsdaine A (2008) Message progression in parallel computing to thread or not to thread?. In: International conference on cluster computing","DOI":"10.1109\/CLUSTR.2008.4663774"},{"key":"327_CR15","doi-asserted-by":"crossref","unstructured":"Didelot S, Carribault P, P\u00e9rache M, Jalby W (2012) Improving MPI communication overlap with collaborative polling. In: EuroMPI","DOI":"10.1007\/978-3-642-33518-1_9"},{"key":"327_CR16","doi-asserted-by":"crossref","unstructured":"Trahay F, Denis A (2009) A scalable and generic task scheduling system for communication libraries. In: International conference on cluster computing","DOI":"10.1109\/CLUSTR.2009.5289169"},{"key":"327_CR17","doi-asserted-by":"crossref","unstructured":"Huang C, Lawlor O, Kal\u00e9 LV (2004) Adaptive MPI. In: LCPC","DOI":"10.1007\/978-3-540-24644-2_20"},{"key":"327_CR18","doi-asserted-by":"crossref","unstructured":"Rico-Gallego JA, Mart\u00edn JCD (2011) Performance evaluation of thread-based MPI in shared memory. In: EuroMPI","DOI":"10.1007\/978-3-642-24449-0_42"},{"key":"327_CR19","unstructured":"Demaine E (1997) A threads-only MPI implementation for the development of parallel programming. In: Proceedings of the 11th international symposium on high performance computing systems"},{"key":"327_CR20","doi-asserted-by":"crossref","unstructured":"Tang H, Yang T (2001) Optimizing threaded MPI execution on SMP clusters. In: International Conference on Supercomputing (ICS)","DOI":"10.1145\/377792.377895"},{"key":"327_CR21","first-page":"80","volume-title":"IWOMP. Lecturen notes in computer science","author":"P Carribault","year":"2011","unstructured":"Carribault P, P\u00e9rache M, Jourdren H (2011) Thread-local storage extension to support thread-based MPI\/openMP applications. In: Chapman BM, Gropp WD, Kumaran K, M\u00fcller MS (eds) IWOMP. Lecturen notes in computer science. Springer, Berlin, pp 80\u201393"},{"key":"327_CR22","unstructured":"InfiniBand Trade Association: InfiniBand architecture specification"},{"key":"327_CR23","unstructured":"Brightwell R, Pedretti K (2011) An intra-node implementation of openshmem using virtual address space mapping. In: Fifth partitioned global address space conference"},{"key":"327_CR24","doi-asserted-by":"crossref","unstructured":"Wolff M, Jaouen S, Jourdren H, Sonnendrcker E (2012) High-order dimensionally split lagrange-remap schemes for ideal magnetohydrodynamics. Discrete and Continuous Dynamical Systems - Series S","DOI":"10.3934\/dcdss.2012.5.345"},{"key":"327_CR25","unstructured":"Bailey D, Harris T, Saphir W, van der Wijngaart R, Woo A, Yarrow M (1995) The NAS Parallel Benchmarks 2.0"},{"key":"327_CR26","doi-asserted-by":"crossref","unstructured":"Springel V (2005) The cosmological simulation code gadget-2. Monthly Notices of the Royal Astronomical Society 364","DOI":"10.1111\/j.1365-2966.2005.09655.x"},{"key":"327_CR27","doi-asserted-by":"crossref","unstructured":"Tezuka H, O\u2019Carroll F, Hori A, Ishikawa Y (1998) Pin-down cache: A virtual memory management technique for zero-copy communication. In: IPPS\/SPDP, pp 308\u2013314","DOI":"10.1109\/IPPS.1998.669932"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0327-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-013-0327-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-013-0327-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,26]],"date-time":"2020-07-26T12:54:48Z","timestamp":1595768088000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-013-0327-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,9]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["327"],"URL":"https:\/\/doi.org\/10.1007\/s00607-013-0327-z","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,5,9]]}}}