{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T14:56:27Z","timestamp":1649084187083},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2014,3,16]],"date-time":"2014-03-16T00:00:00Z","timestamp":1394928000000},"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":[[2014,6]]},"DOI":"10.1007\/s11227-014-1148-3","type":"journal-article","created":{"date-parts":[[2014,3,17]],"date-time":"2014-03-17T21:48:01Z","timestamp":1395092881000},"page":"1184-1213","source":"Crossref","is-referenced-by-count":2,"title":["Building and using application utility models to dynamically choose thread counts"],"prefix":"10.1007","volume":"68","author":[{"given":"Ryan W.","family":"Moore","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruce R.","family":"Childers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,3,16]]},"reference":[{"key":"1148_CR1","doi-asserted-by":"crossref","unstructured":"Moore RW, Childers BR (2012) Using utility prediction models to dynamically choose program thread counts. In: 2012 IEEE international symposium on performance analysis of systems and software (ISPASS). doi: 10.1109\/ISPASS.2012.6189220","DOI":"10.1109\/ISPASS.2012.6189220"},{"key":"1148_CR2","doi-asserted-by":"crossref","unstructured":"Olukotun K, Nayfeh BA, Hammond L, Wilson K, Chang K (1996) The case for a single-chip multiprocessor. In: ASPLOS VII: Proceedings of the seventh international conference on architectural support for programming languages and operating systems. ACM, New York, NY, USA, pp 2\u201311","DOI":"10.1145\/237090.237140"},{"key":"1148_CR3","doi-asserted-by":"crossref","unstructured":"Bienia C, Kumar S, Singh JP, Li K (2008) The PARSEC benchmark suite: characterization and architectural implications. In: Proceedings of the 17th international conference on parallel architectures and compilation techniques, PACT \u201908. ACM, New York. doi: 10.1145\/1454115.1454128","DOI":"10.1145\/1454115.1454128"},{"key":"1148_CR4","doi-asserted-by":"crossref","unstructured":"Moore RW, Childers BR (2011) Inflation and deflation of self-adaptive applications. In: Proceedings of the 6th international symposium on software engineering for adaptive and self-managing systems, SEAMS \u201911. ACM, New York. doi: 10.1145\/1988008.1988041","DOI":"10.1145\/1988008.1988041"},{"key":"1148_CR5","doi-asserted-by":"crossref","unstructured":"Yu C, Petrov P (2010) Adaptive multi-threading for dynamic workloads in embedded multiprocessors. In: Proceedings of the 23rd symposium on integrated circuits and system design, SBCCI \u201910. ACM, New York. doi: 10.1145\/1854153.1854173","DOI":"10.1145\/1854153.1854173"},{"key":"1148_CR6","doi-asserted-by":"crossref","unstructured":"Raman A, Zaks A, Lee JW, August DI (2012) Parcae: a system for flexible parallel execution. In: Proceedings of the 33rd ACM SIGPLAN conference on programming language design and implementation, PLDI \u201912. ACM, New York. doi: 10.1145\/2254064.2254082","DOI":"10.1145\/2254064.2254082"},{"key":"1148_CR7","doi-asserted-by":"crossref","unstructured":"Lee J, Wu H, Ravichandran M, Clark N (2010) Thread tailor: dynamically weaving threads together for efficient, adaptive parallel applications. In: Proceedings of the 37th annual international symposium on computer architecture, ISCA \u201910. ACM, New York. doi: 10.1145\/1815961.1815996","DOI":"10.1145\/1815961.1815996"},{"key":"1148_CR8","doi-asserted-by":"crossref","unstructured":"Bienia C, Li K (2010) Fidelity and scaling of the parsec benchmark inputs. In: 2010 IEEE international symposium on workload characterization (IISWC). doi: 10.1109\/IISWC.2010.5649519","DOI":"10.1109\/IISWC.2010.5649519"},{"key":"1148_CR9","doi-asserted-by":"crossref","unstructured":"Tian K, Jiang Y, Zhang EZ, Shen X (2010) An input-centric paradigm for program dynamic optimizations. In: Proceedings of the ACM international conference on object oriented programming systems languages and applications, OOPSLA \u201910. ACM, New York. doi: 10.1145\/1869459.1869471","DOI":"10.1145\/1869459.1869471"},{"key":"1148_CR10","unstructured":"LuxRender Team (2012) Luxrender v0.8. http:\/\/www.luxrender.net"},{"key":"1148_CR11","doi-asserted-by":"crossref","unstructured":"Conway P, Kalyanasundharam N, Donley G, Lepak K, Hughes B. Cache hierarchy and memory subsystem of the amd opteron processor, Micro, IEEE, 30 (2). doi: 10.1109\/MM.2010.31","DOI":"10.1109\/MM.2010.31"},{"key":"1148_CR12","doi-asserted-by":"crossref","unstructured":"Ahmad SB (2011) On improved processor allocation in 2D mesh-based multicomputers: controlled splitting of parallel requests. In: Proceedings of the 2011 international conference on communication computing and security, ICCCS \u201911. ACM, New York. doi: 10.1145\/1947940.1947984","DOI":"10.1145\/1947940.1947984"},{"key":"1148_CR13","unstructured":"Leung LF, Tsui CY, Ki WH (2004) Minimizing energy consumption of multiple-processors-core systems with simultaneous task allocation, scheduling and voltage assignment. In: Proceedings of the 2004 Asia and South Pacific design automation conference, ASP-DAC \u201904, IEEE Press, Piscataway. http:\/\/portal.acm.org\/citation.cfm?id=1015090.1015267"},{"key":"1148_CR14","doi-asserted-by":"crossref","unstructured":"Kandemir M, Muralidhara SP, Narayanan SHK, Zhang Y, Ozturk O (2009) Optimizing shared cache behavior of chip multiprocessors. In: Proceedings of the 42nd annual IEEE\/ACM international symposium on microarchitecture, MICRO 42. ACM, New York. doi: 10.1145\/1669112.1669176","DOI":"10.1145\/1669112.1669176"},{"key":"1148_CR15","doi-asserted-by":"crossref","unstructured":"Charles P, Grothoff C, Saraswat V, Donawa C, Kielstra A, Ebcioglu K, von Praun C, Sarkar V (2005) X10: an object-oriented approach to nonuniform cluster computing. In: OOPSLA \u201905: Proceedings of the 20th annual ACM SIGPLAN conference on object-oriented programming, systems, languages, and applications. ACM, New York, NY, USA, pp 519\u2013538","DOI":"10.1145\/1094811.1094852"},{"key":"1148_CR16","doi-asserted-by":"crossref","unstructured":"Leiserson CE (2009) The cilk++ concurrency platform. In: Proceedings of the 46th annual design automation conference, DAC \u201909. ACM, New York. doi: 10.1145\/1629911.1630048","DOI":"10.1145\/1629911.1630048"},{"key":"1148_CR17","unstructured":"Architecture Review Board, Openmp application program interface v3.0. http:\/\/www.openmp.org\/mp-documents\/spec30.pdf"},{"key":"1148_CR18","unstructured":"Message Passing Interface Forum, Mpi: a message-passing interface standard version 2.2. http:\/\/www.mpi-forum.org\/docs\/mpi-2.2\/mpi22-report.pdf"},{"key":"1148_CR19","doi-asserted-by":"crossref","unstructured":"Calder B, Grunwald D, Jones M, Lindsay D, Martin J, Mozer M, Zorn B. Evidence-based static branch prediction using machine learning, ACM Trans. Program. Lang. Syst. 19 (1). doi: 10.1145\/239912.239923","DOI":"10.1145\/239912.239923"},{"key":"1148_CR20","doi-asserted-by":"crossref","unstructured":"Chen G, Kandemir M (2005) Optimizing embedded applications using programmer-inserted hints. In: Proceedings of the 2005 Asia and South Pacific design automation conference, ASP-DAC \u201905. ACM, New York. doi: 10.1145\/1120725.1120794","DOI":"10.1145\/1120725.1120794"},{"key":"1148_CR21","doi-asserted-by":"crossref","unstructured":"Suganuma T, Yasue T, Kawahito M, Komatsu H, Nakatani T. Design and evaluation of dynamic optimizations for a java just-in-time compiler, ACM Trans. Program. Lang. Syst. 27 (4). doi: 10.1145\/1075382.1075386","DOI":"10.1145\/1075382.1075386"},{"key":"1148_CR22","doi-asserted-by":"crossref","unstructured":"Maury MC, Dzierwa J, Antonopoulos CD, Nikolopoulos DS (2006) Online power-performance adaptation of multithreaded programs using hardware event-based prediction. In: Proceedings of the 20th annual international conference on supercomputing, ICS \u201906. ACM, New York. doi: 10.1145\/1183401.1183426","DOI":"10.1145\/1183401.1183426"},{"key":"1148_CR23","first-page":"6","volume-title":"Tools for high performance computing 2009","author":"M Itzkowitz","year":"2010","unstructured":"Itzkowitz M, Maruyama Y (2010) HPC profiling with the sun studio performance tools. In: Muller MS, Resch MM, Schulz A, Nagel WE (eds) Tools for high performance computing 2009. Springer, Berlin, p 6. doi: 10.1007\/978-3-642-11261-4_6"},{"key":"1148_CR24","doi-asserted-by":"crossref","unstructured":"Pusukuri KK, Gupta R, Bhuyan LN. Thread tranquilizer: dynamically reducing performance variation, ACM Trans. Archit. Code Optim. 8 (4). doi: 10.1145\/2086696.2086725","DOI":"10.1145\/2086696.2086725"},{"key":"1148_CR25","doi-asserted-by":"crossref","unstructured":"Becchi M, Crowley P (2006) Dynamic thread assignment on heterogeneous multiprocessor architectures. In: Proceedings of the 3rd conference on computing frontiers, CF \u201906. ACM, New York. doi: 10.1145\/1128022.1128029","DOI":"10.1145\/1128022.1128029"},{"key":"1148_CR26","doi-asserted-by":"crossref","unstructured":"Wang Z, O\u2019Boyle MF (2009) Mapping parallelism to multi-cores: a machine learning based approach. In: Proceedings of the 14th ACM SIGPLAN symposium on principles and practice of parallel programming, PPoPP \u201909. ACM, New York. doi: 10.1145\/1504176.1504189","DOI":"10.1145\/1504176.1504189"},{"key":"1148_CR27","doi-asserted-by":"crossref","unstructured":"Martinez JF, Ipek E, Dynamic multicore resource management: a machine learning approach, IEEE Micro 29 (5). doi: 10.1109\/MM.2009.77","DOI":"10.1109\/MM.2009.77"},{"key":"1148_CR28","doi-asserted-by":"crossref","unstructured":"Barnes BJ, Rountree B, Lowenthal DK, Reeves J, de Supinski B, Schulz M (2008) A regression-based approach to scalability prediction. In: Proceedings of the 22nd annual international conference on supercomputing, ICS \u201908. ACM, New York. doi: 10.1145\/1375527.1375580","DOI":"10.1145\/1375527.1375580"},{"key":"1148_CR29","doi-asserted-by":"crossref","unstructured":"Ipek E, de Supinski B, Schulz M, McKee S (2005) An approach to performance prediction for parallel applications Euro-Par 2005 parallel processing. In: Euro-Par 2005 parallel processing, vol. 3648 of Lecture notes in computer science, Springer, Berlin. doi: 10.1007\/11549468_24","DOI":"10.1007\/11549468_24"},{"key":"1148_CR30","doi-asserted-by":"crossref","unstructured":"Lee BC, Brooks DM, de Supinski BR, Schulz M, Singh K, McKee SA (2007) Methods of inference and learning for performance modeling of parallel applications. In: Proceedings of the 12th ACM SIGPLAN symposium on principles and practice of parallel programming, PPoPP \u201907. ACM, New York. doi: 10.1145\/1229428.1229479","DOI":"10.1145\/1229428.1229479"},{"key":"1148_CR31","doi-asserted-by":"crossref","unstructured":"Ipek E, McKee SA, Caruana R, de Supinski BR, Schulz M (2006) Efficiently exploring architectural design spaces via predictive modeling. In: Proceedings of the 12th international conference on architectural support for programming languages and operating systems, ASPLOS-XII. ACM, New York. doi: 10.1145\/1168857.1168882","DOI":"10.1145\/1168857.1168882"},{"key":"1148_CR32","doi-asserted-by":"crossref","unstructured":"Duan R, Nadeem F, Wang J, Zhang Y, Prodan R, Fahringer T (2009) A hybrid intelligent method for performance modeling and prediction of workflow activities in grids. In: Proceedings of the 2009 9th IEEE\/ACM international symposium on cluster computing and the grid, CCGRID \u201909, IEEE Computer Society, Washington. doi: 10.1109\/CCGRID.2009.58","DOI":"10.1109\/CCGRID.2009.58"},{"key":"1148_CR33","doi-asserted-by":"crossref","unstructured":"Zhai J, Chen W, Zheng W (2010) Phantom: predicting performance of parallel applications on large-scale parallel machines using a single node. In: Proceedings of the 15th ACM SIGPLAN symposium on principles and practice of parallel programming, PPoPP \u201910. ACM, New York. doi: 10.1145\/1693453.1693493","DOI":"10.1145\/1693453.1693493"},{"key":"1148_CR34","doi-asserted-by":"crossref","unstructured":"Suleman MA, Qureshi MK, Patt YN (2008) Feedback-driven threading: power-efficient and high-performance execution of multi-threaded workloads on cmps. In: Proceedings of the 13th international conference on architectural support for programming languages and operating systems, ASPLOS XIII. ACM, New York. doi: 10.1145\/1346281.1346317","DOI":"10.1145\/1346281.1346317"},{"key":"1148_CR35","doi-asserted-by":"crossref","unstructured":"Moseley T, Grunwald D, Kihm JL, Connors DA. Methods for modeling resource contention on simultaneous multithreading processors, In: International conference on computer design. doi: 10.1109\/ICCD.2005.74","DOI":"10.1109\/ICCD.2005.74"},{"key":"1148_CR36","volume-title":"AI 2005: advances in artificial intelligence, vol. 3809 of Lecture notes in computer science","author":"D Vengerov","year":"2005","unstructured":"Vengerov D (2005) Adaptive utility-based scheduling in resource-constrained systems. In: Zhang S, Jarvis R (eds) AI 2005: advances in artificial intelligence, vol. 3809 of Lecture notes in computer science. Springer, Berlin"},{"key":"1148_CR37","doi-asserted-by":"crossref","unstructured":"Pusukuri K, Gupta R, Bhuyan L (2011) Thread reinforcer: dynamically determining number of threads via os level monitoring. In: 2011 IEEE international symposium on workload characterization (IISWC). doi: 10.1109\/IISWC.2011.6114208","DOI":"10.1109\/IISWC.2011.6114208"},{"key":"1148_CR38","doi-asserted-by":"crossref","unstructured":"Grewe D, Wang Z, O\u2019Boyle MFP (2011) A workload-aware mapping approach for data-parallel programs. In: Proceedings of the 6th international conference on high performance and embedded architectures and compilers, HiPEAC \u201911. ACM, New York. doi: 10.1145\/1944862.1944881","DOI":"10.1145\/1944862.1944881"},{"key":"1148_CR39","doi-asserted-by":"crossref","unstructured":"De P, Kothari R, Mann V (2007) Identifying sources of operating system jitter through fine-grained kernel instrumentation. In: 2007 IEEE international conference on cluster computing. doi: 10.1109\/CLUSTR.2007.4629247","DOI":"10.1109\/CLUSTR.2007.4629247"},{"key":"1148_CR40","doi-asserted-by":"crossref","unstructured":"De P, Mann V, Mittaly U (2009) Handling os jitter on multicore multithreaded systems. In: IEEE international symposium on parallel distributed processing, 2009. IPDPS 2009. doi: 10.1109\/IPDPS.2009.5161046","DOI":"10.1109\/IPDPS.2009.5161046"},{"key":"1148_CR41","doi-asserted-by":"crossref","unstructured":"Nataraj A, Morris A, Malony AD, Sottile M, Beckman P (2007) The ghost in the machine: observing the effects of kernel operation on parallel application performance. In: Proceedings of the 2007 ACM\/IEEE conference on supercomputing, SC \u201907. ACM, New York. doi: 10.1145\/1362622.1362662","DOI":"10.1145\/1362622.1362662"},{"key":"1148_CR42","doi-asserted-by":"crossref","unstructured":"Shen K (2010) Request behavior variations. In: Proceedings of the 15th edition of ASPLOS on architectural support for programming languages and operating systems. ASPLOS \u201910. ACM, New York. doi: 10.1145\/1736020.1736034","DOI":"10.1145\/1736020.1736034"},{"key":"1148_CR43","doi-asserted-by":"crossref","unstructured":"Constantinou T, Sazeides Y, Michaud P, Fetis D, Seznec A. Performance implications of single thread migration on a chip multi-core, SIGARCH Comput. Archit. News. 33 (4). doi: 10.1145\/1105734.1105745","DOI":"10.1145\/1105734.1105745"},{"key":"1148_CR44","doi-asserted-by":"crossref","unstructured":"Teng Q, Sweeney P, Duesterwald E (2009) Understanding the cost of thread migration for multi-threaded java applications running on a multicore platform. In: IEEE international symposium on performance analysis of systems and software, ISPASS 2009. doi: 10.1109\/ISPASS.2009.4919644","DOI":"10.1109\/ISPASS.2009.4919644"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1148-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-014-1148-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-014-1148-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T10:43:00Z","timestamp":1565260980000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-014-1148-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,3,16]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["1148"],"URL":"https:\/\/doi.org\/10.1007\/s11227-014-1148-3","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,3,16]]}}}