{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:25:20Z","timestamp":1759134320565,"version":"3.37.3"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T00:00:00Z","timestamp":1509408000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["14\/IA\/2474"],"award-info":[{"award-number":["14\/IA\/2474"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s11227-017-2176-6","type":"journal-article","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T15:24:23Z","timestamp":1509463463000},"page":"1321-1340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Hierarchical multicore thread mapping via estimation of remote communication"],"prefix":"10.1007","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4070-7468","authenticated-orcid":false,"given":"Hamidreza","family":"Khaleghzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hossein","family":"Deldari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,31]]},"reference":[{"key":"2176_CR1","doi-asserted-by":"crossref","unstructured":"Gepner P, Kowalik MF (2006) Multi-core processors: new way to achieve high system performance. In: International Symposium on Parallel Computing in Electrical Engineering, 2006. PAR ELEC 2006. IEEE, pp 9\u201313","DOI":"10.1109\/PARELEC.2006.54"},{"key":"2176_CR2","doi-asserted-by":"crossref","unstructured":"Shukla SK, Murthy C, Chande P (2015) A survey of approaches used in parallel architectures and multi-core processors, for performance improvement. In: Progress in Systems Engineering. Springer, pp 537\u2013545","DOI":"10.1007\/978-3-319-08422-0_77"},{"key":"2176_CR3","doi-asserted-by":"crossref","unstructured":"Khammassi N, Le Lann J-C (2014) Design and implementation of a cache hierarchy-aware task scheduling for parallel loops on multicore architectures. PDCTA, Sydney, Australia","DOI":"10.5121\/csit.2014.4237"},{"issue":"2","key":"2176_CR4","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1007\/s11227-014-1092-2","volume":"69","author":"L Zhang","year":"2014","unstructured":"Zhang L, Liu Y, Wang R, Qian D (2014) Lightweight dynamic partitioning for last-level cache of multicore processor on real system. J Supercomput 69(2):547\u2013560","journal-title":"J Supercomput"},{"key":"2176_CR5","doi-asserted-by":"crossref","unstructured":"Sun Z, Wang R, Zhang L, Li Q, Chen L, Wu J, Liu Y (2012) Cache-aware scheduling for energy efficiency on multi-processors. In: 2012 International Conference on Computer Distributed Control and Intelligent Environmental Monitoring (CDCIEM). IEEE, pp 182\u2013186","DOI":"10.1109\/CDCIEM.2012.50"},{"key":"2176_CR6","doi-asserted-by":"crossref","unstructured":"Ding W, Zhang Y, Kandemir M, Srinivas J, Yedlapalli P (2013) Locality-aware mapping and scheduling for multicores. In: 2013 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, pp 1\u201312","DOI":"10.1109\/CGO.2013.6495009"},{"key":"2176_CR7","doi-asserted-by":"crossref","unstructured":"Zhang EZ, Jiang Y, Shen X (2010) Does cache sharing on modern CMP matter to the performance of contemporary multithreaded programs? In: ACM Sigplan Notices. ACM, vol 45, no 5, pp 203\u2013212","DOI":"10.1145\/1693453.1693482"},{"key":"2176_CR8","doi-asserted-by":"crossref","unstructured":"Kazempour V, Fedorova A, Alagheband P (2008) Performance implications of cache affinity on multicore processors. Euro-Par 2008\u2013Parallel Processing, pp 151\u2013161","DOI":"10.1007\/978-3-540-85451-7_17"},{"issue":"1","key":"2176_CR9","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","journal-title":"J Comput Syst Sci"},{"key":"2176_CR10","doi-asserted-by":"crossref","unstructured":"Gir\u00e3o G, de Oliveira BC, Soares R, Silva IS (2007) Cache coherency communication cost in a NoC-based MPSoC platform. In: Proceedings of the 20th Annual Conference on Integrated Circuits and Systems Design. ACM, pp 288\u2013293","DOI":"10.1145\/1284480.1284558"},{"key":"2176_CR11","doi-asserted-by":"crossref","unstructured":"Ramos S, Hoefler T (2013) Modeling communication in cache-coherent SMP systems: a case-study with Xeon Phi. In: Proceedings of the 22nd International Symposium on High-Performance Parallel and Distributed Computing. ACM, pp 97\u2013108","DOI":"10.1145\/2493123.2462916"},{"key":"2176_CR12","doi-asserted-by":"crossref","unstructured":"Song F, Moore S, Dongarra J (2009) Analytical modeling for affinity-based thread scheduling on multicore plataforms. In: Symposium on Principles and Practice of Parallel Programming","DOI":"10.1109\/CLUSTR.2009.5289173"},{"key":"2176_CR13","doi-asserted-by":"crossref","unstructured":"Terboven C, Schmidl D, Jin H, Reichstein T et al (2008) Data and thread affinity in OpenMP programs. In: Proceedings of the 2008 Workshop on Memory Access on Future Processors: A Solved Problem? ACM, pp 377\u2013384","DOI":"10.1145\/1366219.1366222"},{"issue":"2","key":"2176_CR14","first-page":"16","volume":"13","author":"A Anbar","year":"2016","unstructured":"Anbar A, Serres O, Kayraklioglu E, Badawy A-HA, El-Ghazawi T (2016) Exploiting hierarchical locality in deep parallel architectures. ACM Trans Archit Code Optim TACO 13(2):16","journal-title":"ACM Trans Archit Code Optim TACO"},{"key":"2176_CR15","doi-asserted-by":"crossref","unstructured":"Yang T-F, Lin C-H, Yang C-L (2010) Cache-aware task scheduling on multi-core architecture. In: 2010 International Symposium on VLSI Design Automation and Test (VLSI-DAT). IEEE, pp 139\u2013142","DOI":"10.1109\/VDAT.2010.5496710"},{"issue":"2","key":"2176_CR16","first-page":"72","volume":"6","author":"E Wang","year":"2016","unstructured":"Wang E, Ni F, Chen J, Wang H, Li Y (2016) Cache-aware cooperative task mapping in multi-core real-time systems. Int J Inf Electron Eng 6(2):72","journal-title":"Int J Inf Electron Eng"},{"key":"2176_CR17","doi-asserted-by":"crossref","unstructured":"Ghosh M, Nathuji R, Lee M, Schwan K, Lee H-HS (2011) Symbiotic scheduling for shared caches in multi-core systems using memory footprint signature. In: 2011 International Conference on Parallel Processing (ICPP). IEEE, pp 11\u201320","DOI":"10.1109\/ICPP.2011.72"},{"issue":"1","key":"2176_CR18","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.jpdc.2010.08.020","volume":"71","author":"JC Saez","year":"2011","unstructured":"Saez JC, Shelepov D, Fedorova A, Prieto M (2011) Leveraging workload diversity through os scheduling to maximize performance on single-isa heterogeneous multicore systems. J Parallel Distrib Comput 71(1):114\u2013131","journal-title":"J Parallel Distrib Comput"},{"issue":"2","key":"2176_CR19","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1145\/1531793.1531804","volume":"43","author":"D Shelepov","year":"2009","unstructured":"Shelepov D, Saez Alcaide JC, Jeffery S, Fedorova A, Perez N, Huang ZF, Blagodurov S, Kumar V (2009) Hass: a scheduler for heterogeneous multicore systems. ACM SIGOPS Oper Syst Rev 43(2):66\u201375","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"2176_CR20","doi-asserted-by":"crossref","unstructured":"Luo H, Li P, Ding C (2017) Thread data sharing in cache: theory and measurement. In: Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. ACM, pp 103\u2013115","DOI":"10.1145\/3018743.3018759"},{"key":"2176_CR21","doi-asserted-by":"crossref","unstructured":"Luk C-K, Cohn R, Muth R, Patil H, Klauser A, Lowney G, Wallace S, Reddi VJ, Hazelwood K (2005) Pin: building customized program analysis tools with dynamic instrumentation. In: ACM SIGPLAN Notices. ACM, vol 40, no 6, pp 190\u2013200","DOI":"10.1145\/1065010.1065034"},{"issue":"2","key":"2176_CR22","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1147\/sj.92.0078","volume":"9","author":"RL Mattson","year":"1970","unstructured":"Mattson RL, Gecsei J, Slutz DR, Traiger IL (1970) Evaluation techniques for storage hierarchies. IBM Syst J 9(2):78\u2013117","journal-title":"IBM Syst J"},{"key":"2176_CR23","unstructured":"Shelepov D, Fedorova A (2008) Scheduling on heterogeneous multicore processors using architectural signatures"},{"issue":"1","key":"2176_CR24","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1137\/S1064827595287997","volume":"20","author":"G Karypis","year":"1998","unstructured":"Karypis G, Kumar V (1998) A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J Sci Comput 20(1):359\u2013392","journal-title":"SIAM J Sci Comput"},{"key":"2176_CR25","doi-asserted-by":"crossref","unstructured":"Ranger C, Raghuraman R, Penmetsa A, Bradski G, Kozyrakis C (2007) Evaluating mapreduce for multi-core and multiprocessor systems. In: IEEE 13th International Symposium on High Performance Computer Architecture, 2007. HPCA 2007. IEEE, pp 13\u201324","DOI":"10.1109\/HPCA.2007.346181"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-017-2176-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2176-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2176-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,5]],"date-time":"2019-10-05T07:37:59Z","timestamp":1570261079000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-017-2176-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,31]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["2176"],"URL":"https:\/\/doi.org\/10.1007\/s11227-017-2176-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2017,10,31]]}}}