{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T14:40:57Z","timestamp":1775054457790,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,9,18]],"date-time":"2013-09-18T00:00:00Z","timestamp":1379462400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s11227-013-1018-4","type":"journal-article","created":{"date-parts":[[2013,9,17]],"date-time":"2013-09-17T14:00:27Z","timestamp":1379426427000},"page":"565-584","source":"Crossref","is-referenced-by-count":3,"title":["Measurement of the latency parameters of the Multi-BSP model: a multicore benchmarking approach"],"prefix":"10.1007","volume":"67","author":[{"given":"Abdorreza","family":"Savadi","sequence":"first","affiliation":[]},{"given":"Hossein","family":"Deldari","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,9,18]]},"reference":[{"key":"1018_CR1","doi-asserted-by":"crossref","first-page":"1116","DOI":"10.1145\/48529.48535","volume":"31","author":"A Aggarwal","year":"1988","unstructured":"Aggarwal A, Vitter JS (1988) The input\/output complexity of sorting and related problems. Commun ACM 31:1116\u20131127. doi: 10.1145\/48529.48535","journal-title":"Commun ACM"},{"key":"1018_CR2","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1007\/BF01185206","volume":"12","author":"B Alpern","year":"1994","unstructured":"Alpern B, Carter L, Feig E, Selker T (1994) The uniform memory hierarchy model of computation. Algorithmica 12:72\u2013109. doi: 10.1007\/BF01185206","journal-title":"Algorithmica"},{"key":"1018_CR3","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1145\/1378533.1378573","volume-title":"Proceedings of the twentieth annual symposium on parallelism in algorithms and architectures, SPAA \u201908","author":"L Arge","year":"2008","unstructured":"Arge L, Goodrich MT, Nelson M, Sitchinava N (2008) Fundamental parallel algorithms for private-cache chip multiprocessors. In: Proceedings of the twentieth annual symposium on parallelism in algorithms and architectures, SPAA \u201908. ACM, New York, pp 197\u2013206. http:\/\/doi.acm.org\/10.1145\/1378533.1378573"},{"key":"1018_CR4","first-page":"197","volume-title":"20th ACM symposium on parallelism in algorithm and architectures (SPAA)","author":"L Arge","year":"2008","unstructured":"Arge L, Goodrich MT, Sitchinava N, Nelson M (2008) Fundamental parallel algorithms for privatecache chip multiprocessors. In: 20th ACM symposium on parallelism in algorithm and architectures (SPAA). ACM, New York, pp 197\u2013206"},{"key":"1018_CR5","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1145\/125826.125925","volume-title":"Supercomputing, 1991. Proceedings of the 1991 ACM\/IEEE conference on supercomputing","author":"D Bailey","year":"1991","unstructured":"Bailey D, Barszcz E, Barton J, Browning D, Carter R, Dagum L, Fatoohi R, Frederickson P, Lasinski T, Schreiber R, Simon H, Venkatakrishnan V, Weeratunga S (1991) The nas parallel benchmarks summary and preliminary results. In: Supercomputing, 1991. Proceedings of the 1991 ACM\/IEEE conference on supercomputing, pp 158\u2013165"},{"key":"1018_CR6","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780198529392.001.0001","volume-title":"Parallel scientific computation: a structured approach using BSP and MPI","author":"RH Bisseling","year":"2004","unstructured":"Bisseling RH (2004) Parallel scientific computation: a structured approach using BSP and MPI. Oxford University Press, Oxford"},{"key":"1018_CR7","first-page":"501","volume-title":"Proceedings of the nineteenth annual ACM-SIAM symposium on discrete algorithms, SODA \u201908","author":"GE Blelloch","year":"2008","unstructured":"Blelloch GE, Chowdhury RA, Gibbons PB, Ramachandran V, Chen S, Kozuch M (2008) Provably good multicore cache performance for divide-and-conquer algorithms. In: Proceedings of the nineteenth annual ACM-SIAM symposium on discrete algorithms, SODA \u201908. Society for Industrial and Applied Mathematics, Philadelphia, pp 501\u2013510. http:\/\/portal.acm.org\/citation.cfm?id=1347082.1347137"},{"key":"1018_CR8","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1145\/1989493.1989553","volume-title":"Proceedings of the 23rd ACM symposium on parallelism in algorithms and architectures, SPAA \u201911","author":"GE Blelloch","year":"2011","unstructured":"Blelloch GE, Fineman JT, Gibbons PB, Simhadri HV (2011) Scheduling irregular parallel computations on hierarchical caches. In: Proceedings of the 23rd ACM symposium on parallelism in algorithms and architectures, SPAA \u201911. ACM, New York, pp 355\u2013366. http:\/\/doi.acm.org\/10.1145\/1989493.1989553"},{"key":"1018_CR9","unstructured":"Butenhof DR Programming with POSIX threads. Addison-Wesley"},{"key":"1018_CR10","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/IISWC.2009.5306797","volume-title":"Proceedings of international symposium on workload characterization, IISWC2009","author":"S Che","year":"2009","unstructured":"Che S, Boyer M, Meng J, Tarjan D, Sheaffer J, Lee SH, Skadron K (2009) Servet: a benchmark suite for autotuning on multicore clusters. In: Proceedings of international symposium on workload characterization, IISWC2009, pp 44\u201354"},{"key":"1018_CR11","first-page":"1","volume-title":"IEEE international symposium on parallel distributed processing (IPDPS)","author":"R Chowdhury","year":"2010","unstructured":"Chowdhury R, Silvestri F, Blakeley B, Ramachandran V (2010) Oblivious algorithms for multicores and network of processors. In: IEEE international symposium on parallel distributed processing (IPDPS), pp 1\u201312"},{"key":"1018_CR12","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1145\/240455.240477","volume":"39","author":"DE Culler","year":"1996","unstructured":"Culler DE, Karp RM, Patterson D, Sahay A, Santos EE, Schauser KE, Subramonian R, von Eicken T (1996) Logp: a practical model of parallel computation. Commun ACM 39:78\u201385. http:\/\/doi.acm.org\/10.1145\/240455.240477","journal-title":"Commun ACM"},{"key":"1018_CR13","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1145\/800133.804339","volume-title":"Proceedings of the tenth annual ACM symposium on theory of computing, STOC \u201978","author":"S Fortune","year":"1978","unstructured":"Fortune S, Wyllie J (1978) Parallelism in random access machines. In: Proceedings of the tenth annual ACM symposium on theory of computing, STOC \u201978. ACM, New York, pp 114\u2013118. http:\/\/doi.acm.org\/10.1145\/800133.804339"},{"key":"1018_CR14","first-page":"285","volume-title":"Annual IEEE symposium on foundations of computer science","author":"M Frigo","year":"1999","unstructured":"Frigo M, Leiserson CE, Prokop H, Ramachandran S (1999) Cache-oblivious algorithms. In: Annual IEEE symposium on foundations of computer science, p 285"},{"key":"1018_CR15","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1109\/MC.2008.464","volume":"41","author":"S Gal-On","year":"2008","unstructured":"Gal-On S, Levy M (2008) Measuring multicore performance. Computer 41:99\u2013102","journal-title":"Computer"},{"issue":"3","key":"1018_CR16","first-page":"169","volume":"12","author":"AV Gerbessiotis","year":"2004","unstructured":"Gerbessiotis AV, Lee SY (2004) Remote memory access: a case for portable, efficient and library independent parallel programming. Sci Program 12(3):169\u2013183. http:\/\/dl.acm.org\/citation.cfm?id=1240140.1240144","journal-title":"Sci Program"},{"key":"1018_CR17","first-page":"1","volume-title":"Proceedings of international symposium on parallel and distributed processing, IPDPS2010","author":"J Gonzalez-Dominguez","year":"2010","unstructured":"Gonzalez-Dominguez J, Taboada G, Fraguela B, Martin M, Tourio J (2010) Servet: a benchmark suite for autotuning on multicore clusters. In: Proceedings of international symposium on parallel and distributed processing, IPDPS2010, pp 1\u20139"},{"key":"1018_CR18","unstructured":"Hill JMD, Donaldson SR, Skillicorn DB (1997) Stability of communication performance in practice: From the cray t3e to networks of workstations. Technical Report PRG-TR-33-97, Programming Research Group, Oxford University Computing Laboratory"},{"key":"1018_CR19","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1109\/EMPDP.1998.647231","volume-title":"6th EuroMicro workshop on parallel and distributed processing (PDP\u201998)","author":"JMD Hill","year":"1998","unstructured":"Hill JMD, Skillicorn DB (1998) Practical barrier synchronisation. In: 6th EuroMicro workshop on parallel and distributed processing (PDP\u201998). IEEE Computer Society Press, Los Alamitos, pp 438\u2013444"},{"issue":"14","key":"1018_CR20","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1016\/S0167-8191(98)00093-3","volume":"24","author":"JM Hill","year":"1998","unstructured":"Hill JM, McColl B, Stefanescu DC, Goudreau MW, Lang K, Rao SB, Suel T, Tsantilas T, Bisseling RH (1998) Bsplib: the bsp programming library. Parallel Comput 24(14):1947\u20131980. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167819198000933","journal-title":"Parallel Comput"},{"key":"1018_CR21","volume-title":"Proceedings of 21th international parallel and distributed processing symposium, IPDPS2007","author":"A Kayi","year":"2007","unstructured":"Kayi A, Yao Y, El-Ghazawi T, Newby G (2007) Experimental evaluation of emerging multi-core architectures. In: Proceedings of 21th international parallel and distributed processing symposium, IPDPS2007"},{"key":"1018_CR22","unstructured":"Linux-operating-systems. http:\/\/linux.die.net"},{"issue":"1","key":"1018_CR23","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1145\/103727.103729","volume":"9","author":"JM Mellor-Crummey","year":"1991","unstructured":"Mellor-Crummey JM, Scott ML (1991) Algorithms for scalable synchronization on shared-memory multiprocessors. ACM Trans Comput Syst 9(1):21\u201365. http:\/\/doi.acm.org\/10.1145\/103727.103729","journal-title":"ACM Trans Comput Syst"},{"key":"1018_CR24","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BFb0058018","volume-title":"Foundations of software technology and theoretical computer science","author":"V Ramachandran","year":"1997","unstructured":"Ramachandran V (1997) Qsm: a general purpose shared-memory model for parallel computation. In: Ramesh S, Sivakumar G (eds) Foundations of software technology and theoretical computer science. Lecture notes in computer science, vol 1346. Springer, Berlin, pp 1\u20135. doi: 10.1007\/BFb0058018"},{"issue":"4","key":"1018_CR25","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/1105734.1105743","volume":"33","author":"J Sampson","year":"2005","unstructured":"Sampson J, Gonz\u00e1lez R, Collard JF, Jouppi NP, Schlansker M (2005) Fast synchronization for chip multiprocessors. SIGARCH Comput Archit News 33(4):64\u201369. http:\/\/doi.acm.org\/10.1145\/1105734.1105743","journal-title":"SIGARCH Comput Archit News"},{"key":"1018_CR26","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1007\/BFb0030842","volume-title":"Computing and combinatorics","author":"J Savage","year":"1995","unstructured":"Savage J (1995) Extending the hong-kung model to memory hierarchies. In: Du DZ, Li M (eds) Computing and combinatorics. Lecture notes in computer science, vol 959. Springer, Berlin, pp 270\u2013281. doi: 10.1007\/BFb0030842"},{"key":"1018_CR27","first-page":"9:1","volume-title":"Proceedings of the 1st international forum on next-generation multicore\/manycore technologies, IFMT \u201908","author":"JE Savage","year":"2008","unstructured":"Savage JE, Zubair M (2008) A unified model for multicore architectures. In: Proceedings of the 1st international forum on next-generation multicore\/manycore technologies, IFMT \u201908. ACM, New York, pp 9:1\u20139:12. http:\/\/doi.acm.org\/10.1145\/1463768.1463780"},{"issue":"1","key":"1018_CR28","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/130823.130824","volume":"20","author":"JP Singh","year":"1992","unstructured":"Singh JP, Weber WD, Gupta A (1992) Splash: Stanford parallel applications for shared-memory. SIGARCH Comput Archit News 20(1):5\u201344. http:\/\/doi.acm.org\/10.1145\/130823.130824","journal-title":"SIGARCH Comput Archit News"},{"key":"1018_CR29","unstructured":"S.P.E.C.S. benchmarks http:\/\/www.spec.org\/"},{"key":"1018_CR30","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"LG Valiant","year":"1990","unstructured":"Valiant LG (1990) A bridging model for parallel computation. Commun ACM 33:103\u2013111. http:\/\/doi.acm.org\/10.1145\/79173.79181","journal-title":"Commun ACM"},{"issue":"1","key":"1018_CR31","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.jcss.2010.06.012","volume":"77","author":"LG Valiant","year":"2011","unstructured":"Valiant LG (2011) A bridging model for multi-core computing. J Comput Syst Sci 77(1):154\u2013166. http:\/\/www.sciencedirect.com\/science\/article\/B6WJ0-508X3P4-5\/2\/92a9dec04839a9e93887ca26e0d9b3f2 , celebrating Karp\u2019s Kyoto Prize","journal-title":"J Comput Syst Sci"},{"key":"1018_CR32","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1109\/VDAT.2010.5496710","volume-title":"2010 international symposium on VLSI design automation and test (VLSI-DAT)","author":"TF Yang","year":"2010","unstructured":"Yang TF, Lin CH, Yang CL (2010) Cache-aware task scheduling on multi-core architecture. In: 2010 international symposium on VLSI design automation and test (VLSI-DAT), pp 139\u2013142. doi: 10.1109\/VDAT.2010.5496710"},{"key":"1018_CR33","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1145\/1248377.1248394","volume-title":"Proceedings of the nineteenth annual ACM symposium on parallel algorithms and architectures, SPAA \u201907","author":"K Yotov","year":"2007","unstructured":"Yotov K, Roeder T, Pingali K, Gunnels J, Gustavson F (2007) An experimental comparison of cache-oblivious and cache-conscious programs. In: Proceedings of the nineteenth annual ACM symposium on parallel algorithms and architectures, SPAA \u201907. ACM, New York, pp 93\u2013104. http:\/\/doi.acm.org\/10.1145\/1248377.1248394"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1018-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-013-1018-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-1018-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,24]],"date-time":"2019-07-24T04:50:09Z","timestamp":1563943809000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-013-1018-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,18]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["1018"],"URL":"https:\/\/doi.org\/10.1007\/s11227-013-1018-4","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,18]]}}}