{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T01:17:19Z","timestamp":1768871839193,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2018,2,2]],"date-time":"2018-02-02T00:00:00Z","timestamp":1517529600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"EU FP7","award":["609666"],"award-info":[{"award-number":["609666"]}]},{"name":"GINOP","award":["GINOP-2.3.2-15-2016-00037"],"award-info":[{"award-number":["GINOP-2.3.2-15-2016-00037"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s11227-018-2252-6","type":"journal-article","created":{"date-parts":[[2018,2,2]],"date-time":"2018-02-02T02:08:13Z","timestamp":1517537293000},"page":"4001-4025","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Prediction models for performance, power, and energy efficiency of software executed on heterogeneous hardware"],"prefix":"10.1007","volume":"75","author":[{"given":"D\u00e9nes","family":"B\u00e1n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8897-7403","authenticated-orcid":false,"given":"Rudolf","family":"Ferenc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4064-1489","authenticated-orcid":false,"given":"Istv\u00e1n","family":"Siket","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u00c1kos","family":"Kiss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tibor","family":"Gyim\u00f3thy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,2]]},"reference":[{"key":"2252_CR1","unstructured":"(2014) NVIDIA Management Library (NVML)\u2014Reference Manual. NVIDIA Corporation, TRM-06719-001 _vR331"},{"key":"2252_CR2","unstructured":"(2014) PicoScope 4000 Series (A API)\u2014Programmers Guide. Pico Technology Ltd., ps4000apg.en r1"},{"key":"2252_CR3","unstructured":"(2015) AMD GPU Performance API\u2014User Guide. Advanced Micro Devices, Inc., v2.15"},{"key":"2252_CR4","unstructured":"(2015) ARM DS-5 Version 5.21\u2014Streamline User Guide. ARM, ARM DUI0482S"},{"key":"2252_CR5","unstructured":"(2015) Intel 64 and IA-32 Architectures Software Developer\u2019s Manual: vol 3B. Intel Corporation, Order Number 253669"},{"key":"2252_CR6","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1214\/09-SS054","volume":"4","author":"S Arlot","year":"2010","unstructured":"Arlot S, Celisse A (2010) A survey of cross-validation procedures for model selection. Stat Surv 4:40\u201379","journal-title":"Stat Surv"},{"key":"2252_CR7","unstructured":"B\u00e1n D, Ferenc R, Siket I, Kiss \u00c1 (2015) Prediction models for performance, power, and energy efficiency of software executed on heterogeneous hardware. In: Proceedings of the 13th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA 2015). IEEE, pp 178\u2013183"},{"key":"2252_CR8","unstructured":"B\u00e1n D, Ferenc R, Siket I, Kiss \u00c1, Gyim\u00f3thy T (2017) Performance, power, and energy prediction models. \n                    http:\/\/www.inf.u-szeged.hu\/~ferenc\/papers\/PerformancePowerEnergyModels\/"},{"key":"2252_CR9","unstructured":"B\u00e1n D, Sipka R, Dobi I (2017) Tagged parallel benchmarks. \n                    https:\/\/github.com\/sed-inf-u-szeged\/TaggedParallelBenchmarks"},{"key":"2252_CR10","doi-asserted-by":"crossref","unstructured":"Brandolese C, Fornaciari W, Salice F, Sciuto D (2001) Source-level execution time estimation of C programs. In: Proceedings of the Ninth International Symposium on Hardware\/Software Codesign (CODES). ACM, New York, NY, USA, pp 98\u2013103","DOI":"10.1145\/371636.371694"},{"key":"2252_CR11","doi-asserted-by":"crossref","unstructured":"Brown KJ, Sujeeth AK, Lee HJ, Rompf T, Chafi H, Odersky M, Olukotun K (2011) A heterogeneous parallel framework for domain-specific languages. In: Proceedings of the 2011 International Conference on Parallel Architectures and Compilation Techniques. IEEE Computer Society, pp 89\u2013100","DOI":"10.1109\/PACT.2011.15"},{"key":"2252_CR12","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/IISWC.2009.5306797","volume-title":"IEEE International Symposium on Workload Characterization (IISWC)","author":"S Che","year":"2009","unstructured":"Che S, Boyer M, Meng J, Tarjan D, Sheaffer J, Lee SH, Skadron K (2009) Rodinia: a benchmark suite for heterogeneous computing. IEEE International Symposium on Workload Characterization (IISWC). IEEE Computer Society, Washington, DC, USA, pp 44\u201354"},{"key":"2252_CR13","unstructured":"Ferenc R et\u00a0al (2014) Static analysis techniques for AIR generation. Deliverable D2.2, REPARA"},{"key":"2252_CR14","unstructured":"Ferenc R et\u00a0al (2015) Maintainability models of heterogeneous programming models. Deliverable D7.4, REPARA"},{"key":"2252_CR15","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/s10766-010-0161-2","volume":"39","author":"G Fursin","year":"2011","unstructured":"Fursin G, Kashnikov Y, Memon AW, Chamski Z, Temam O, Namolaru M, Yom-Tov E, Mendelson B, Zaks A, Courtois E, Bodin F, Barnard P, Ashton E, Bonilla E, Thomson J, Williams CKI, O\u2019Boyle M (2011) Milepost GCC: machine learning enabled self-tuning compiler. Int J Parallel Program 39:296\u2013327","journal-title":"Int J Parallel Program"},{"key":"2252_CR16","doi-asserted-by":"crossref","unstructured":"Grauer-Gray S, Xu L, Searles R, Ayalasomayajula S, Cavazos J (2012) Auto-tuning a high-level language targeted to GPU codes. In: Innovative Parallel Computing (InPar). IEEE, pp 1\u201310","DOI":"10.1109\/InPar.2012.6339595"},{"key":"2252_CR17","doi-asserted-by":"crossref","unstructured":"Grewe D, O\u2019Boyle MFP (2011) A static task partitioning approach for heterogeneous systems using OpenCL. In: Proceedings of the 20th International Conference Compiler Construction (CC). Springer, Berlin, Heidelberg, pp 286\u2013305","DOI":"10.1007\/978-3-642-19861-8_16"},{"key":"2252_CR18","doi-asserted-by":"crossref","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The WEKA data mining software: an update. In: SIGKDD Explorations, ACM, vol\u00a011, pp 10\u201318","DOI":"10.1145\/1656274.1656278"},{"key":"2252_CR19","unstructured":"Kiss \u00c1, Moln\u00e1r P, Sipka R (2017) RMeasure performance and energy monitoring library. \n                    https:\/\/github.com\/sed-inf-u-szeged\/RMeasure"},{"key":"2252_CR20","doi-asserted-by":"crossref","unstructured":"Kuperberg M, Krogmann K, Reussner R (2008) Performance prediction for black-box components using reengineered parametric behaviour models. In: Proceedings of the 11th International Symposium on Component-Based Software Engineering. Springer, pp 48\u201363","DOI":"10.1007\/978-3-540-87891-9_4"},{"key":"2252_CR21","doi-asserted-by":"crossref","unstructured":"Li D, de\u00a0Supinski B, Schulz M, Cameron K, Nikolopoulos D (2010) Hybrid MPI\/OpenMP power-aware computing. In: IEEE International Symposium on Parallel Distributed Processing (IPDPS). IEEE, pp 1\u201312","DOI":"10.1109\/IPDPS.2010.5470463"},{"key":"2252_CR22","unstructured":"Ma X, Dong M, Zhong L, Deng Z (2009) Statistical power consumption analysis and modeling for GPU-based computing. In: In Proceedings of SOSP Workshop on Power-aware Computing and Systems (HotPower)\u201909"},{"key":"2252_CR23","doi-asserted-by":"crossref","unstructured":"Marin G, Mellor-Crummey J (2004) Cross-architecture performance predictions for scientific applications using parameterized models. In: Proceedings of the Joint International Conference on Measurement and Modeling of Computer Systems. ACM, pp 2\u201313","DOI":"10.1145\/1005686.1005691"},{"key":"2252_CR24","doi-asserted-by":"crossref","unstructured":"Osmulski T, Muehring JT, Veale B, West JM, Li H, Vanichayobon S, Ko SH, Antonio JK, Dhall SK (2000) A probabilistic power prediction tool for the Xilinx 4000-series FPGA. In: Proceedings of the IPDPS 2000 Workshops on Parallel and Distributed Processing. Springer, pp 776\u2013783","DOI":"10.1007\/3-540-45591-4_107"},{"key":"2252_CR25","unstructured":"Pfl\u00fcger D, Pfander D (2016) Computational efficiency vs. maintainability and portability. Experiences with the sparse grid code sg++. In: Proceedings of the Fourth International Workshop on Software Engineering for High Performance Computing in Computational Science and Engineering (SE-HPCCSE). IEEE, pp 17\u201325"},{"key":"2252_CR26","unstructured":"Pouchet LN (2011) Polybench: the polyhedral benchmark suite. \n                    http:\/\/www-roc.inria.fr\/~pouchet\/software\/polybench"},{"key":"2252_CR27","unstructured":"S\u00e1nchez LM et\u00a0al (2014) Target platform description specification. Deliverable D3.1, REPARA"},{"key":"2252_CR28","first-page":"116","volume-title":"41st International Conference on Parallel Processing Workshops (ICPPW)","author":"J Shen","year":"2012","unstructured":"Shen J, Fang J, Sips H, Varbanescu A (2012) Performance gaps between OpenMP and OpenCL for multi-core CPUs. 41st International Conference on Parallel Processing Workshops (ICPPW). IEEE Computer Society, Washington, DC, USA, pp 116\u2013125"},{"key":"2252_CR29","unstructured":"Stratton JA, Rodrigues C, Sung IJ, Obeid N, Chang LW, Anssari N, Liu GD, Mei W,\u00a0Hwu W (2012) Parboil: a revised benchmark suite for scientific and commercial throughput computing. Technical report, University of Illinois at Urbana-Champaign"},{"key":"2252_CR30","doi-asserted-by":"crossref","unstructured":"Takizawa H, Sato K, Kobayashi H (2008) SPRAT: Runtime processor selection for energy-aware computing. In: IEEE International Conference on Cluster Computing. IEEE, pp 386\u2013393","DOI":"10.1109\/CLUSTR.2008.4663799"},{"key":"2252_CR31","volume-title":"Asymptotic statistics, Cambridge series in statistical and probabilistic mathematics","author":"A Vaart Van Der","year":"1998","unstructured":"Van Der Vaart A (1998) Asymptotic statistics, Cambridge series in statistical and probabilistic mathematics, vol 3. Cambridge University Press, Cambridge"},{"key":"2252_CR32","doi-asserted-by":"crossref","unstructured":"Yang L, Ma X, Mueller F (2005) Cross-platform performance prediction of parallel applications using partial execution. In: Proceedings of the ACM\/IEEE SC 2005 Conference on Supercomputing. IEEE Computer Society, Washington, DC, USA, p\u00a040","DOI":"10.1109\/SC.2005.20"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-2252-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2252-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2252-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T11:23:10Z","timestamp":1568200990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-2252-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,2]]},"references-count":32,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["2252"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-2252-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,2]]},"assertion":[{"value":"2 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}