{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:47:46Z","timestamp":1786981666102,"version":"build-2736575974"},"reference-count":126,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T00:00:00Z","timestamp":1599696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T00:00:00Z","timestamp":1599696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1007\/s11227-020-03417-5","type":"journal-article","created":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T04:40:39Z","timestamp":1599712839000},"page":"4014-4055","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Performance prediction of parallel applications: a systematic literature review"],"prefix":"10.1007","volume":"77","author":[{"given":"Jesus","family":"Flores-Contreras","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2069-4711","authenticated-orcid":false,"given":"Hector A.","family":"Duran-Limon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arturo","family":"Chavoya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio H.","family":"Almanza-Ruiz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,10]]},"reference":[{"issue":"3","key":"3417_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/71.80155","volume":"1","author":"VW Mak","year":"1990","unstructured":"Mak VW, Lundstrom SF (1990) Predicting performance of parallel computations. IEEE Trans Parallel Distrib Syst 1(3):257\u2013270. https:\/\/doi.org\/10.1109\/71.80155","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3417_CR2","doi-asserted-by":"publisher","unstructured":"Mielke RR, Stoughton JW, Som S (1988) Modeling and performance bounds for concurrent processing. In: 8th International Conference on Distributed Computing Systems, 1988, pp 538\u2013544. https:\/\/doi.org\/10.1109\/DCS.1988.12557","DOI":"10.1109\/DCS.1988.12557"},{"issue":"11","key":"3417_CR3","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1109\/71.250100","volume":"4","author":"S Som","year":"1993","unstructured":"Som S, Mielke RR, Stoughton JW (1993) Prediction of performance and processor requirements in real-time data flow architectures. IEEE Trans Parallel Distrib Syst 4(11):1205\u20131216. https:\/\/doi.org\/10.1109\/71.250100","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3417_CR4","doi-asserted-by":"publisher","unstructured":"Kundu S, Rangaswami R, Dutta K, Zhao M (2010) Application performance modeling in a virtualized environment. In: 2010 IEEE 16th International Symposium on High Performance Computer Architecture (HPCA), pp 1 \u201310. https:\/\/doi.org\/10.1109\/HPCA.2010.5463058","DOI":"10.1109\/HPCA.2010.5463058"},{"issue":"12","key":"3417_CR5","doi-asserted-by":"publisher","first-page":"30\u201330:40","DOI":"10.1145\/2076796.2082137","volume":"9","author":"A Oliner","year":"2011","unstructured":"Oliner A, Ganapathi A, Xu W (2011) Advances and challenges in log analysis: logs contain a wealth of information for help in managing systems. Queue 9(12):30\u201330:40. https:\/\/doi.org\/10.1145\/2076796.2082137","journal-title":"Queue"},{"issue":"6","key":"3417_CR6","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.future.2007.07.003","volume":"24","author":"Y Zhang","year":"2008","unstructured":"Zhang Y, Sun W, Inoguchi Y (2008) Predict task running time in grid environments based on CPU load predictions. Future Gener Comput Syst 24(6):489\u2013497. https:\/\/doi.org\/10.1016\/j.future.2007.07.003","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR7","unstructured":"Kitchenham B (2004) Procedures for performing systematic reviews. Technical report Keele University and Empirical Software Engineering National ICT Australia Ltd"},{"issue":"6","key":"3417_CR8","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TSE.2011.103","volume":"38","author":"T Hall","year":"2012","unstructured":"Hall T, Beecham S, Bowes D, Gray D, Counsell S (2012) A systematic literature review on fault prediction performance in software engineering. IEEE Trans Softw Eng 38(6):1276\u20131304","journal-title":"IEEE Trans Softw Eng"},{"key":"3417_CR9","unstructured":"Chen L, Ali Babar M, Ali N (2009) Variability management in software product lines: a systematic review. In: Proceedings of the 13th International Software Product Line Conference, SPLC\u201909, Carnegie Mellon University, Pittsburgh, PA, USA, pp 81\u201390"},{"issue":"1","key":"3417_CR10","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MSPEC.2022.9676364","volume":"48","author":"SK Moore","year":"2011","unstructured":"Moore SK (2011) Multicore CPUs: processor proliferation. IEEE Spectr 48(1):40\u201343","journal-title":"IEEE Spectr"},{"issue":"2","key":"3417_CR11","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1007\/s11192-012-0938-8","volume":"96","author":"P K\u00fcngas","year":"2013","unstructured":"K\u00fcngas P, Karus S, Vakulenko S, Dumas M, Parra C, Casati F (2013) Reverse-engineering conference rankings: what does it take to make a reputable conference? Scientometrics 96(2):651\u2013665. https:\/\/doi.org\/10.1007\/s11192-012-0938-8","journal-title":"Scientometrics"},{"key":"3417_CR12","unstructured":"(2010) E. A. of Australasia (CORE), Conference rankings. http:\/\/www.core.edu.au\/conference-portal. Consulted April 2020"},{"key":"3417_CR13","first-page":"101","volume-title":"Measuring the impact of scientific research","author":"PUK De Silva","year":"2017","unstructured":"De Silva PUK, Vance CK (2017) Measuring the impact of scientific research. Springer International Publishing, Cham, pp 101\u2013115"},{"issue":"5","key":"3417_CR14","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.surge.2013.08.002","volume":"12","author":"JC Oosthuizen","year":"2014","unstructured":"Oosthuizen JC, Fenton JE (2014) Alternatives to the impact factor. Surgeon 12(5):239\u2013243. https:\/\/doi.org\/10.1016\/j.surge.2013.08.002","journal-title":"Surgeon"},{"issue":"3","key":"3417_CR15","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1007\/s11192-016-2136-6","volume":"109","author":"JL C\u00e1novas Izquierdo","year":"2016","unstructured":"C\u00e1novas Izquierdo JL, Cosentino V, Cabot J (2016) Analysis of co-authorship graphs of CORE-ranked software conferences. Scientometrics 109(3):1665\u20131693. https:\/\/doi.org\/10.1007\/s11192-016-2136-6","journal-title":"Scientometrics"},{"issue":"4","key":"3417_CR16","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1109\/TSE.2010.59","volume":"37","author":"N Salleh","year":"2011","unstructured":"Salleh N, Mendes E, Grundy J (2011) Empirical studies of pair programming for CS\/SE teaching in higher education: a systematic literature review. IEEE Trans Softw Eng 37(4):509\u2013525. https:\/\/doi.org\/10.1109\/TSE.2010.59","journal-title":"IEEE Trans Softw Eng"},{"issue":"12","key":"3417_CR17","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1016\/j.jss.2009.07.020","volume":"82","author":"S Shimizu","year":"2009","unstructured":"Shimizu S, Rangaswami R, Duran-Limon HA, Corona-Perez M (2009) Platform-independent modeling and prediction of application resource usage characteristics. J Syst Softw 82(12):2117\u20132127. https:\/\/doi.org\/10.1016\/j.jss.2009.07.020","journal-title":"J Syst Softw"},{"key":"3417_CR18","doi-asserted-by":"publisher","DOI":"10.21236\/ADA637068","volume-title":"A model for speedup of parallel programs","author":"AB Downey","year":"1997","unstructured":"Downey AB (1997) A model for speedup of parallel programs. Technical report, USA"},{"issue":"6","key":"3417_CR19","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1109\/TPDS.2009.128","volume":"21","author":"M Drozdowski","year":"2010","unstructured":"Drozdowski M, Wielebski L (2010) Isoefficiency maps for divisible computations. IEEE Trans Parallel Distrib Syst 21(6):872\u2013880. https:\/\/doi.org\/10.1109\/TPDS.2009.128","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"3417_CR20","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/88.242438","volume":"1","author":"AY Grama","year":"1993","unstructured":"Grama AY, Gupta A, Kumar V (1993) Isoefficiency: measuring the scalability of parallel algorithms and architectures. IEEE Parallel Distrib Technol Syst Appl 1(3):12\u201321. https:\/\/doi.org\/10.1109\/88.242438","journal-title":"IEEE Parallel Distrib Technol Syst Appl"},{"key":"3417_CR21","unstructured":"Collins GW (2003) Fundamental numerical methods and data analysis. http:\/\/ads.harvard.edu\/books\/1990fnmd.book\/"},{"key":"3417_CR22","doi-asserted-by":"publisher","unstructured":"Smyth GK (2005) Polynomial approximation. In: Armitage P, Colton T (eds) Encyclopedia of biostatistics. https:\/\/doi.org\/10.1002\/0470011815.b2a14028","DOI":"10.1002\/0470011815.b2a14028"},{"key":"3417_CR23","doi-asserted-by":"publisher","unstructured":"Li Y, Ma W (2010) Applications of artificial neural networks in financial economics: a survey. In: 2010 International Symposium on Computational Intelligence and Design (ISCID), vol 1, pp 211\u2013214. https:\/\/doi.org\/10.1109\/ISCID.2010.70","DOI":"10.1109\/ISCID.2010.70"},{"issue":"1\u20135","key":"3417_CR24","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1023\/A:1006559212014","volume":"11","author":"CG Atkeson","year":"1997","unstructured":"Atkeson CG, Moore AW, Schaal S (1997) Locally weighted learning. Artif Intell Rev 11(1\u20135):11\u201373. https:\/\/doi.org\/10.1023\/A:1006559212014","journal-title":"Artif Intell Rev"},{"key":"3417_CR25","unstructured":"Hein JL (2002) Discrete mathematics, Chap. 10, 2nd edn. Jones and Bartlett Publishers, Inc., Burlington, p 560"},{"key":"3417_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/b138744","author":"PL Bonate","year":"2006","unstructured":"Bonate PL (2006) Pharmacokinetic-pharmacodynamic modeling and simulation. Springer, US, New York. https:\/\/doi.org\/10.1007\/b138744","journal-title":"Springer, US, New York."},{"key":"3417_CR27","volume-title":"NonLinear regression","author":"GAF Seber","year":"2003","unstructured":"Seber GAF, Wild CJ (2003) Nonlinear regression. Wiley Interscience, Hoboken"},{"issue":"8","key":"3417_CR28","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.1109\/TPDS.2017.2669305","volume":"28","author":"A Degomme","year":"2017","unstructured":"Degomme A, Legrand A, Markomanolis GS, Quinson M, Stillwell M, Suter F (2017) Simulating MPI applications: the SMPI approach. IEEE Trans Parallel Distrib Syst 28(8):2387\u20132400","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3417_CR29","doi-asserted-by":"publisher","unstructured":"Yang LT, Ma X, Mueller F (2005) Cross-platform performance prediction of parallel applications using partial execution. In: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing, SC\u201905, IEEE Computer Society, Seattle, WA, USA, p 40. https:\/\/doi.org\/10.1109\/SC.2005.20","DOI":"10.1109\/SC.2005.20"},{"key":"3417_CR30","doi-asserted-by":"publisher","unstructured":"Litke A, Tserpes K, Varvarigou T (2005) Computational workload prediction for grid oriented industrial applications: the case of 3D-image rendering. In: IEEE International Symposium on Cluster Computing and the Grid, 2005. CCGrid 2005, vol 2, pp 962\u2013969. https:\/\/doi.org\/10.1109\/CCGRID.2005.1558665","DOI":"10.1109\/CCGRID.2005.1558665"},{"issue":"6","key":"3417_CR31","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/j.future.2007.06.001","volume":"24","author":"E Elmroth","year":"2008","unstructured":"Elmroth E, Tordsson J (2008) Grid resource brokering algorithms enabling advance reservations and resource selection based on performance predictions. Future Gener Comput Syst 24(6):585\u2013593. https:\/\/doi.org\/10.1016\/j.future.2007.06.001","journal-title":"Future Gener Comput Syst"},{"issue":"10","key":"3417_CR32","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1016\/j.jpdc.2006.05.008","volume":"66","author":"M Wu","year":"2006","unstructured":"Wu M, Sun X-H (2006) Grid harvest service: a performance system of grid computing. J Parallel Distrib Comput 66(10):1322\u20131337. https:\/\/doi.org\/10.1016\/j.jpdc.2006.05.008","journal-title":"J Parallel Distrib Comput"},{"issue":"2","key":"3417_CR33","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPDS.2019.2938172","volume":"31","author":"Y Cho","year":"2020","unstructured":"Cho Y, Oh S, Egger B (2020) Performance modeling of parallel loops on multi-socket platforms using queueing systems. IEEE Trans Parallel Distrib Syst 31(2):318\u2013331","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"3417_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3309684","volume":"29","author":"J Bhimani","year":"2019","unstructured":"Bhimani J, Mi N, Leeser M, Yang Z (2019) New performance modeling methods for parallel data processing applications. ACM Trans Model Comput Simul 29(3):1. https:\/\/doi.org\/10.1145\/3309684","journal-title":"ACM Trans Model Comput Simul"},{"key":"3417_CR35","doi-asserted-by":"publisher","unstructured":"Heinecke A (2013) Accelerators in scientific computing is it worth the effort? In: 2013 International Conference on High Performance Computing and Simulation (HPCS), 2013, p 504. https:\/\/doi.org\/10.1109\/HPCSim.2013.6641460","DOI":"10.1109\/HPCSim.2013.6641460"},{"key":"3417_CR36","doi-asserted-by":"publisher","unstructured":"El-Khamra Y, Gaffney N, Walling D, Wernert E, Xu W, Zhang H (2013) Performance evaluation of R with Intel Xeon Phi coprocessor. In: 2013 IEEE International Conference on Big Data, pp 23\u201330. https:\/\/doi.org\/10.1109\/BigData.2013.6691695","DOI":"10.1109\/BigData.2013.6691695"},{"key":"3417_CR37","doi-asserted-by":"publisher","unstructured":"Heinecke A, Vaidyanathan K, Smelyanskiy M, Kobotov A, Dubtsov R, Henry G, Shet AG, Chrysos G, Dubey P (2013) Design and implementation of the Linpack benchmark for single and multi-node systems based on Intel \u00ae Xeon Phi coprocessor. In: 2013 IEEE 27th International Symposium on Parallel Distributed Processing (IPDPS), pp 126\u2013137. https:\/\/doi.org\/10.1109\/IPDPS.2013.113","DOI":"10.1109\/IPDPS.2013.113"},{"key":"3417_CR38","doi-asserted-by":"publisher","unstructured":"Misra G, Kurkure N, Das A, Valmiki M, Das S, Gupta A (2013) Evaluation of Rodinia codes on Intel Xeon Phi. In: 2013 4th International Conference on Intelligent Systems Modelling Simulation (ISMS), pp 415\u2013419. https:\/\/doi.org\/10.1109\/ISMS.2013.118","DOI":"10.1109\/ISMS.2013.118"},{"key":"3417_CR39","doi-asserted-by":"publisher","unstructured":"Ramachandran A, Vienne J, Van Der Wijngaart R, Koesterke L, Sharapov I (2013) Performance evaluation of NAS parallel benchmarks on Intel Xeon Phi. In: 2013 42nd International Conference on Parallel Processing (ICPP), pp 736\u2013743. https:\/\/doi.org\/10.1109\/ICPP.2013.87","DOI":"10.1109\/ICPP.2013.87"},{"key":"3417_CR40","unstructured":"(2019) Top500 list, November 2019 release. www.top500.org"},{"key":"3417_CR41","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1142\/9789812701831_0012","volume-title":"Use of high performance computing in meteorology","author":"J Michalakes","year":"2005","unstructured":"Michalakes J, Dudhia J, Gill D, Henderson T, Klemp J, Skamarock W, Wang W (2005) The weather research and forecast model: software architecture and performance. In: Zwieflhofer W, Mozdzynski G (eds) Use of high performance computing in meteorology. World Scientific, Reading UK, pp 156\u2013168"},{"issue":"4","key":"3417_CR42","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams S, Waterman A, Patterson D (2009) Roofline: an insightful visual performance model for multicore architectures. Commun ACM 52(4):65\u201376. https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun ACM"},{"key":"3417_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-020-03248-4","author":"K Haghshenas","year":"2020","unstructured":"Haghshenas K, Mohammadi S (2020) Prediction-based underutilized and destination host selection approaches for energy-efficient dynamic VM consolidation in data centers. J Supercomput. https:\/\/doi.org\/10.1007\/s11227-020-03248-4","journal-title":"J Supercomput"},{"key":"3417_CR44","doi-asserted-by":"crossref","unstructured":"Farahnakian F, Pahikkala T, Liljeberg P, Plosila J, Tenhunen H (2015) Utilization prediction aware VM consolidation approach for green cloud computing. In: 2015 IEEE 8th International Conference on Cloud Computing, pp 381\u2013388","DOI":"10.1109\/CLOUD.2015.58"},{"issue":"2","key":"3417_CR45","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.suscom.2012.03.002","volume":"3","author":"M Murugan","year":"2013","unstructured":"Murugan M, Du DHC, Kant K (2013) On the interconnect energy efficiency of high end computing systems. Sustain Comput Inform Syst 3(2):49\u201357. https:\/\/doi.org\/10.1016\/j.suscom.2012.03.002","journal-title":"Sustain Comput Inform Syst"},{"key":"3417_CR46","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.future.2013.07.012","volume":"36","author":"M Jarus","year":"2014","unstructured":"Jarus M, Oleksiak A, Piontek T, W\u0119glarz J (2014) Runtime power usage estimation of HPC servers for various classes of real-life applications. Future Gener Comput Syst 36:299\u2013310. https:\/\/doi.org\/10.1016\/j.future.2013.07.012","journal-title":"Future Gener Comput Syst"},{"issue":"1","key":"3417_CR47","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.future.2012.06.003","volume":"29","author":"M Witkowski","year":"2013","unstructured":"Witkowski M, Oleksiak A, Piontek T, W\u0119glarz J (2013) Practical power consumption estimation for real life HPC applications. Future Gener Comput Syst 29(1):208\u2013217. https:\/\/doi.org\/10.1016\/j.future.2012.06.003","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR48","unstructured":"Darling A, Carey L, Feng WC (2003) The design, implementation, and evaluation of mpiBLAST. In Proceedings of the ClusterWorld Conference and Expo and the 4th International Conference on Linux Clusters: The HPC Revolution 2003. http:\/\/public.lanl.gov\/radiant\/pubs\/bio\/cwce03.pdf"},{"key":"3417_CR49","unstructured":"Heroux MA (2015) miniFE a finite element mini-application. https:\/\/asc.llnl.gov\/CORAL-benchmarks\/#minife"},{"key":"3417_CR50","doi-asserted-by":"publisher","first-page":"31371","DOI":"10.1039\/C5CP00351B","volume":"17","author":"X Andrade","year":"2015","unstructured":"Andrade X, Strubbe DA, Giovannini UD, Larsen AH, Oliveira MJT, Alberdi-Rodriguez J, Varas A, Theophilou I, Helbig N, Verstraete M, Stella L, Nogueira F, Aspuru-Guzik A, Castro A, Marques MAL, Rubio A (2015) Real-space grids and the Octopus code as tools for the development of new simulation approaches for electronic systems. Phys. Chem. Chem. Phys 17:31371\u201331396. https:\/\/doi.org\/10.1039\/C5CP00351B","journal-title":"Phys. Chem. Chem. Phys"},{"issue":"6","key":"3417_CR51","first-page":"731","volume":"52","author":"P Altenbernd","year":"2016","unstructured":"Altenbernd P, Gustafsson J, Lisper B, Stappert F (2016) Early execution time-estimation through automatically generated timing models, Real-Time Systems: The International Journal of Time-Critical. Comput Syst 52(6):731\u2013760","journal-title":"Comput Syst"},{"key":"3417_CR52","doi-asserted-by":"crossref","unstructured":"Amaris M, Cordeiro D, Goldman A, Camargo RYd (2015) A simple BSP-based model to predict execution time in GPU applications. In: 2015 IEEE 22nd International Conference on High Performance Computing (HiPC), pp 285\u2013294","DOI":"10.1109\/HiPC.2015.34"},{"key":"3417_CR53","doi-asserted-by":"publisher","unstructured":"Bauer G, Gottlieb S, Hoefler T (2012) Performance modeling and comparative analysis of the MILC lattice QCD application su3_rmd. In: 2012 12th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp 652\u2013659. https:\/\/doi.org\/10.1109\/CCGrid.2012.123","DOI":"10.1109\/CCGrid.2012.123"},{"key":"3417_CR54","doi-asserted-by":"publisher","unstructured":"Boull\u00f3n M, Cabaleiro JC, Doallo R, Gonz\u00e1lez P, Mart\u00ednez DR, Mart\u00edn M, Mouri\u00f1o JC, Pena TF, Rivera F (2005) Modeling execution time of selected computation and communication kernels on grids. In: Sloot PMA, Hoekstra AG, Priol T, Reinefeld A, Bubak M (eds) Advances in grid computing\u2014EGC 2005, volume 3470 of lecture notes in computer science. Springer, Heidelberg, pp 731\u2013740. https:\/\/doi.org\/10.1007\/11508380_74","DOI":"10.1007\/11508380_74"},{"key":"3417_CR55","doi-asserted-by":"publisher","unstructured":"Calotoiu A, Hoefler T, Poke M, Wolf F (2013) Using automated performance modeling to find scalability bugs in complex codes. In: SC\u201913: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp 1\u201312. https:\/\/doi.org\/10.1145\/2503210.2503277","DOI":"10.1145\/2503210.2503277"},{"issue":"3","key":"3417_CR56","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.future.2004.11.019","volume":"22","author":"L Carrington","year":"2006","unstructured":"Carrington L, Snavely A, Wolter N (2006) A performance prediction framework for scientific applications. Future Gener Comput Syst 22(3):336\u2013346. https:\/\/doi.org\/10.1016\/j.future.2004.11.019","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR57","doi-asserted-by":"crossref","unstructured":"Choi J, Richards DF, Kale LV, Bhatele A (2020) End-to-end performance modeling of distributed GPU applications. In: Proceedings of the 34th ACM International Conference on Supercomputing, pp 1\u201312","DOI":"10.1145\/3392717.3392737"},{"issue":"3","key":"3417_CR58","doi-asserted-by":"publisher","first-page":"1609","DOI":"10.1007\/s11227-012-0823-5","volume":"62","author":"BF Cornea","year":"2012","unstructured":"Cornea BF, Bourgeois J (2012) A framework for efficient performance prediction of distributed applications in heterogeneous systems. J Supercomput 62(3):1609\u20131634. https:\/\/doi.org\/10.1007\/s11227-012-0823-5","journal-title":"J Supercomput"},{"issue":"3\u20134","key":"3417_CR59","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s00450-011-0164-2","volume":"26","author":"JA Davis","year":"2011","unstructured":"Davis JA, Mudalige GR, Hammond SD, Herdman JA, Miller I, Jarvis SA (2011) Predictive analysis of a hydrodynamics application on large-scale CMP clusters. Comput Sci 26(3\u20134):175\u2013185. https:\/\/doi.org\/10.1007\/s00450-011-0164-2","journal-title":"Comput Sci"},{"issue":"2","key":"3417_CR60","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/LCA.2018.2849983","volume":"17","author":"S De Pestel","year":"2018","unstructured":"De Pestel S, Van den Steen S, Akram S, Eeckhout L (2018) RPPM: rapid performance prediction of multithreaded applications on multicore hardware. IEEE Comput Archit Lett 17(2):183\u2013186","journal-title":"IEEE Comput Archit Lett"},{"key":"3417_CR61","doi-asserted-by":"publisher","unstructured":"Gianni D, Iazeolla G, D\u2019Ambrogio A (2010) A methodology to predict the performance of distributed simulations. In: 2010 IEEE Workshop on Principles of Advanced and Distributed Simulation (PADS), pp 1\u20139. https:\/\/doi.org\/10.1109\/PADS.2010.5471669","DOI":"10.1109\/PADS.2010.5471669"},{"issue":"3","key":"3417_CR62","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.parco.2007.01.001","volume":"33","author":"A Gualandris","year":"2007","unstructured":"Gualandris A, Zwart SP, Tirado-Ramos A (2007) Performance analysis of direct N-body algorithms for astrophysical simulations on distributed systems. Parallel Comput 33(3):159\u2013173. https:\/\/doi.org\/10.1016\/j.parco.2007.01.001","journal-title":"Parallel Comput"},{"key":"3417_CR63","doi-asserted-by":"publisher","unstructured":"Guo P, wei Lee C (2016) A performance prediction and analysis integrated framework for SpMV on GPUs. Procedia Comput Sci 80:178\u2013189. International conference on computational science 2016, ICCS 2016, 6\u20138 June 2016, San Diego, California, USA. https:\/\/doi.org\/10.1016\/j.procs.2016.05.308","DOI":"10.1016\/j.procs.2016.05.308"},{"key":"3417_CR64","doi-asserted-by":"publisher","unstructured":"Hammer J, Hager G, Eitzinger J, Wellein G (2015) Automatic loop kernel analysis and performance modeling with Kerncraft. In: Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems, PMBS \u201815, Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2832087.2832092","DOI":"10.1145\/2832087.2832092"},{"key":"3417_CR65","doi-asserted-by":"publisher","unstructured":"Hudik M, Hodon M (2014) Modeling, optimization and performance prediction of parallel algorithms. In: 2014 IEEE Symposium on Computers and Communication (ISCC), Workshops, pp 1\u20137. https:\/\/doi.org\/10.1109\/ISCC.2014.6912632","DOI":"10.1109\/ISCC.2014.6912632"},{"issue":"4","key":"3417_CR66","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1134\/S0361768806040037","volume":"32","author":"VP Ivannikov","year":"2006","unstructured":"Ivannikov VP, Gaisaryan SS, Avetisyan AI, Padaryan VA (2006) Estimation of dynamical characteristics of a parallel program on a model. Program Comput Softw 32(4):203\u2013214. https:\/\/doi.org\/10.1134\/S0361768806040037","journal-title":"Program Comput Softw"},{"key":"3417_CR67","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1016\/j.future.2006.02.008","volume":"22","author":"SA Jarvis","year":"2006","unstructured":"Jarvis SA, Spooner DP, Keung HNLC, Cao J, Saini S, Nudd GR (2006) Performance prediction and its use in parallel and distributed computing systems. Future Gener Comput Syst 22:745\u2013754. https:\/\/doi.org\/10.1016\/j.future.2006.02.008","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR68","doi-asserted-by":"publisher","unstructured":"Kerbyson DJ, Barker KJ (2011) A performance model of direct numerical simulation for analyzing large-scale systems. In: 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and PhD Forum (IPDPSW), pp 1824\u20131830. https:\/\/doi.org\/10.1109\/IPDPS.2011.341","DOI":"10.1109\/IPDPS.2011.341"},{"key":"3417_CR69","doi-asserted-by":"publisher","unstructured":"Kestor G, Gioiosa R, Chavarr\u0131a-Miranda D (2015) Prometheus: scalable and accurate emulation of task-based applications on many-core systems. In: 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp 308\u2013317. https:\/\/doi.org\/10.1109\/ISPASS.2015.7095816","DOI":"10.1109\/ISPASS.2015.7095816"},{"key":"3417_CR70","doi-asserted-by":"publisher","unstructured":"Lee S, Meredith JS, Vetter JS (2015) COMPASS: a framework for automated performance modeling and prediction. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS\u201915. ACM, New York, NY, USA, pp 405\u2013414. https:\/\/doi.org\/10.1145\/2751205.2751220","DOI":"10.1145\/2751205.2751220"},{"issue":"6","key":"3417_CR71","doi-asserted-by":"publisher","first-page":"2506","DOI":"10.1007\/s11227-016-1943-0","volume":"73","author":"D Li","year":"2017","unstructured":"Li D, Xu C, Cheng B, Xiong M, Gao X, Deng X (2017) Performance modeling and optimization of parallel LU-SGS on many-core processors for 3D high-order CFD simulations. J Supercomput 73(6):2506\u20132524","journal-title":"J Supercomput"},{"issue":"5","key":"3417_CR72","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/s10766-005-7303-y","volume":"33","author":"ET Midorikawa","year":"2005","unstructured":"Midorikawa ET, de Oliveira HM, Laine JM (2005) PEMPIs: a new methodology for modeling and prediction of MPI programs performance. Int J Parallel Prog 33(5):499\u2013527. https:\/\/doi.org\/10.1007\/s10766-005-7303-y","journal-title":"Int J Parallel Prog"},{"key":"3417_CR73","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1016\/j.future.2019.10.007","volume":"111","author":"A Mohammed","year":"2020","unstructured":"Mohammed A, Eleliemy A, Ciorba FM, Kasielke F, Banicescu I (2020) An approach for realistically simulating the performance of scientific applications on high performance computing systems. Future Gener Comput Syst 111:617\u2013633","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR74","doi-asserted-by":"crossref","unstructured":"Obaida MA, Liu J, Chennupati G, Santhi N, Eidenbenz S (2018) Parallel application performance prediction using analysis based models and HPC simulations. In: Proceedings of the 2018 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, pp 49\u201359","DOI":"10.1145\/3200921.3200937"},{"key":"3417_CR75","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1016\/j.procs.2013.05.351","volume":"18","author":"J Panadero","year":"2013","unstructured":"Panadero J, Wong A, Rexachs D, Luque E (2013) A tool for selecting the right target machine for parallel scientific applications. Procedia Comput Sci 18:1824\u20131833. https:\/\/doi.org\/10.1016\/j.procs.2013.05.351. 2013 International Conference on Computational Science","journal-title":"Procedia Comput Sci"},{"key":"3417_CR76","doi-asserted-by":"publisher","unstructured":"Parakh AK, Balakrishnan M, Paul K (2012) Performance estimation of GPUs with cache. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops PhD Forum (IPDPSW), pp 2384\u20132393. https:\/\/doi.org\/10.1109\/IPDPSW.2012.328","DOI":"10.1109\/IPDPSW.2012.328"},{"key":"3417_CR77","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.06.011","author":"J Sahuquillo","year":"2015","unstructured":"Sahuquillo J, Hassan H, Petit S, March JL, Duato J (2015) A dynamic execution time estimation model to save energy in heterogeneous multicores running periodic tasks. Future Gener Comput Syst. https:\/\/doi.org\/10.1016\/j.future.2015.06.011","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR78","doi-asserted-by":"crossref","unstructured":"Saussard R, Bouzid B, Vasiliu M, Reynaud R (2015) Optimal performance prediction of ADAS algorithms on embedded parallel architectures. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems, pp 213\u2013218","DOI":"10.1109\/HPCC-CSS-ICESS.2015.95"},{"issue":"3","key":"3417_CR79","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.future.2010.09.004","volume":"27","author":"S Seneviratne","year":"2011","unstructured":"Seneviratne S, Levy DC (2011) Task profiling model for load profile prediction. Future Gener Comput Syst 27(3):245\u2013255. https:\/\/doi.org\/10.1016\/j.future.2010.09.004","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR80","doi-asserted-by":"publisher","unstructured":"Sharkawi S, DeSota D, Panda R, Stevens S, Taylor V, Wu X (2012) SWAPP: a framework for performance projections of HPC applications using benchmarks. In: 2012 IEEE 26th International parallel and distributed processing symposium workshops PhD forum (IPDPSW), pp 1722\u20131731. https:\/\/doi.org\/10.1109\/IPDPSW.2012.214","DOI":"10.1109\/IPDPSW.2012.214"},{"issue":"1","key":"3417_CR81","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/s10766-012-0232-7","volume":"42","author":"E Sun","year":"2014","unstructured":"Sun E, Kaeli D (2014) Aggressive value prediction on a GPU. Int J Parallel Program 42(1):30\u201348","journal-title":"Int J Parallel Program"},{"key":"3417_CR82","doi-asserted-by":"publisher","unstructured":"Tallent NR, Hoisie A (2014) Palm: Easing the burden of analytical performance modeling. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS\u201914. Association for Computing Machinery, New York, NY, USA, pp 221\u2013230 https:\/\/doi.org\/10.1145\/2597652.2597683","DOI":"10.1145\/2597652.2597683"},{"key":"3417_CR83","doi-asserted-by":"crossref","unstructured":"Wang K, Khan MMH (2015) Performance prediction for apache spark platform. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems, pp 166\u2013173","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"issue":"7","key":"3417_CR84","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1109\/TPDS.2014.2329688","volume":"26","author":"A Wong","year":"2015","unstructured":"Wong A, Rexachs D, Luque E (2015) Parallel application signature for performance analysis and prediction. IEEE Trans Parallel Distrib Syst 26(7):2009\u20132019. https:\/\/doi.org\/10.1109\/TPDS.2014.2329688","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"9","key":"3417_CR85","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPDS.2019.2905213","volume":"30","author":"J Wu","year":"2019","unstructured":"Wu J, Yang X, Zhang Z, Chen G, Mao R (2019) A performance model for GPU architectures that considers on-chip resources: Application to medical image registration. IEEE Trans Parallel Distrib Syst 30(9):1947\u20131961","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"4","key":"3417_CR86","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.peva.2005.01.008","volume":"63","author":"EJH Yero","year":"2006","unstructured":"Yero EJH, Henriques MAA (2006) Contention-sensitive static performance prediction for parallel distributed applications. Perform Eval 63(4):265\u2013277. https:\/\/doi.org\/10.1016\/j.peva.2005.01.008","journal-title":"Perform Eval"},{"key":"3417_CR87","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1109\/TC.2015.2479630","volume":"65","author":"J Zhai","year":"2016","unstructured":"Zhai J, Chen W, Zheng W, Li K (2016) Performance prediction for large-scale parallel applications using representative replay. IEEE Trans Comput 65:2184\u20132198","journal-title":"IEEE Trans Comput"},{"key":"3417_CR88","doi-asserted-by":"publisher","unstructured":"Achour S, Ammar M, Khmili B, Nasri W (2011) MPI-PERF-SIM: towards an automatic performance prediction tool of MPI programs on hierarchical clusters. In: 2011 19th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), pp 207\u2013211. https:\/\/doi.org\/10.1109\/PDP.2011.49","DOI":"10.1109\/PDP.2011.49"},{"issue":"9","key":"3417_CR89","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1007\/s11265-020-01563-w","volume":"92","author":"OJ Arndt","year":"2020","unstructured":"Arndt OJ, L\u00fcders M, Riggers C, Blume H (2020) Multicore performance prediction with MPET. J Signal Process Syst 92(9):981\u2013998","journal-title":"J Signal Process Syst"},{"key":"3417_CR90","doi-asserted-by":"publisher","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, NY, USA, pp 368\u2013377. https:\/\/doi.org\/10.1145\/1375527.1375580","DOI":"10.1145\/1375527.1375580"},{"key":"3417_CR91","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.simpat.2017.05.009","volume":"77","author":"P Czarnul","year":"2017","unstructured":"Czarnul P, Kuchta J, Matuszek M, Proficz J, Ro\u015bciszewski P, W\u00f3jcik M (2017) Szyma\u0144ski J MERPSYS: an environment for simulation of parallel application execution on large scale HPC systems. Simul Model Pract Theory 77:124\u2013140. https:\/\/doi.org\/10.1016\/j.simpat.2017.05.009","journal-title":"Simul Model Pract Theory"},{"key":"3417_CR92","doi-asserted-by":"crossref","unstructured":"De Sensi D (2016) Predicting performance and power consumption of parallel applications. In: 2016 24th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), pp 200\u2013207","DOI":"10.1109\/PDP.2016.41"},{"key":"3417_CR93","doi-asserted-by":"publisher","unstructured":"Deshmeh A, Machina J, Sodan A (2010) ADEPT scalability predictor in support of adaptive resource allocation. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS), pp 1\u201312. https:\/\/doi.org\/10.1109\/IPDPS.2010.5470430","DOI":"10.1109\/IPDPS.2010.5470430"},{"key":"3417_CR94","doi-asserted-by":"publisher","unstructured":"Goldsmith SF, Aiken AS, Wilkerson DS (2007) Measuring empirical computational complexity. In: Proceedings of the the 6th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, ESEC-FSE\u201907. Association for Computing Machinery, New York, NY, USA, pp 395\u2013404. https:\/\/doi.org\/10.1145\/1287624.1287681","DOI":"10.1145\/1287624.1287681"},{"key":"3417_CR95","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.entcs.2006.09.033","volume":"182","author":"J Happe","year":"2007","unstructured":"Happe J, Koziolek H, Reussner R (2007) Parametric performance contracts for software components with concurrent behaviour. Electron Notes Theor Comput Sci 182:91\u2013106. https:\/\/doi.org\/10.1016\/j.entcs.2006.09.033","journal-title":"Electron Notes Theor Comput Sci"},{"issue":"2","key":"3417_CR96","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s11227-006-7554-4","volume":"38","author":"E-N Huh","year":"2006","unstructured":"Huh E-N, Welch LR (2006) Adaptive resource management for dynamic distributed real-time applications. J Supercomput 38(2):127\u2013142. https:\/\/doi.org\/10.1007\/s11227-006-7554-4","journal-title":"J Supercomput"},{"issue":"2","key":"3417_CR97","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1109\/TPDS.2015.2405552","volume":"27","author":"M Khan","year":"2016","unstructured":"Khan M, Jin Y, Li M, Xiang Y, Jiang C (2016) Hadoop performance modeling for job estimation and resource provisioning. IEEE Trans Parallel Distrib Syst 27(2):441\u2013454","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3417_CR98","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.future.2018.08.018","volume":"90","author":"G Lu","year":"2019","unstructured":"Lu G, Zhang W, He H, Yang LT (2019) Performance modeling for MPI applications with low overhead fine-grained profiling. Future Gener Comput Syst 90:317\u2013326","journal-title":"Future Gener Comput Syst"},{"issue":"6","key":"3417_CR99","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1016\/j.jpdc.2013.01.011","volume":"73","author":"O Lobachev","year":"2013","unstructured":"Lobachev O, Guthe M, Loogen R (2013) Estimating parallel performance. J Parallel Distrib Comput 73(6):876\u2013887. https:\/\/doi.org\/10.1016\/j.jpdc.2013.01.011","journal-title":"J Parallel Distrib Comput"},{"issue":"1","key":"3417_CR100","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s11227-008-0215-z","volume":"49","author":"RF de Mello","year":"2009","unstructured":"de Mello RF, Yang LT (2009) Prediction of dynamical, nonlinear, and unstable process behavior. J Supercomput 49(1):22\u201341. https:\/\/doi.org\/10.1007\/s11227-008-0215-z","journal-title":"J Supercomput"},{"key":"3417_CR101","doi-asserted-by":"publisher","unstructured":"Pfeiffer W, Wright NJ (2008) Modeling and predicting application performance on parallel computers using HPC challenge benchmarks. In: IEEE International Symposium on Parallel and Distributed Processing, 2008. IPDPS 2008, pp 1\u201312. https:\/\/doi.org\/10.1109\/IPDPS.2008.4536278","DOI":"10.1109\/IPDPS.2008.4536278"},{"key":"3417_CR102","doi-asserted-by":"crossref","unstructured":"Sadjadi SM, Shimizu S, Figueroa J, Rangaswami R, Delgado J, Duran H, Collazo-Mojica XJ (2008) A modeling approach for estimating execution time of long-running scientific applications. In: 2008 IEEE International Symposium on Parallel and Distributed Processing, pp 1\u20138","DOI":"10.1109\/IPDPS.2008.4536214"},{"issue":"8","key":"3417_CR103","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1016\/j.jpdc.2008.02.006","volume":"68","author":"HA Sanjay","year":"2008","unstructured":"Sanjay HA, Vadhiyar S (2008) Performance modeling of parallel applications for grid scheduling. J Parallel Distrib Comput 68(8):1135\u20131145. https:\/\/doi.org\/10.1016\/j.jpdc.2008.02.006","journal-title":"J Parallel Distrib Comput"},{"issue":"2","key":"3417_CR104","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10586-007-0039-2","volume":"11","author":"S Sodhi","year":"2008","unstructured":"Sodhi S, Subhlok J, Xu Q (2008) Performance prediction with skeletons. Clust Comput 11(2):151\u2013165. https:\/\/doi.org\/10.1007\/s10586-007-0039-2","journal-title":"Performance prediction with skeletons. Clust Comput"},{"issue":"4","key":"3417_CR105","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s10732-015-9292-3","volume":"22","author":"C Truchet","year":"2016","unstructured":"Truchet C, Arbelaez A, Richoux F, Codognet P (2016) Estimating parallel runtimes for randomized algorithms in constraint solving. J Heuristics 22(4):613\u2013648. https:\/\/doi.org\/10.1007\/s10732-015-9292-3","journal-title":"J Heuristics"},{"issue":"10","key":"3417_CR106","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1016\/j.peva.2008.04.001","volume":"65","author":"R Wu","year":"2008","unstructured":"Wu R, Sun J, Chen J (2008) Parallel execution time prediction of the multitask parallel programs. Perform Eval 65(10):701\u2013713. https:\/\/doi.org\/10.1016\/j.peva.2008.04.001","journal-title":"Perform Eval"},{"issue":"11","key":"3417_CR107","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1016\/j.jpdc.2008.06.007","volume":"68","author":"Y Chen","year":"2008","unstructured":"Chen Y, Sun X-H, Wu M (2008) Algorithm-system scalability of heterogeneous computing. J Parallel Distrib Comput 68(11):1403\u20131412. https:\/\/doi.org\/10.1016\/j.jpdc.2008.06.007","journal-title":"J Parallel Distrib Comput"},{"key":"3417_CR108","doi-asserted-by":"publisher","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, NY, USA, pp 305\u2013314. https:\/\/doi.org\/10.1145\/1693453.1693493","DOI":"10.1145\/1693453.1693493"},{"key":"3417_CR109","doi-asserted-by":"publisher","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, SIGMETRICS\u201904\/Performance\u201904. ACM, New York, NY, USA, pp 2\u201313. https:\/\/doi.org\/10.1145\/1005686.1005691","DOI":"10.1145\/1005686.1005691"},{"issue":"2","key":"3417_CR110","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1007\/s11227-012-0748-z","volume":"62","author":"M Chtepen","year":"2012","unstructured":"Chtepen M, Claeys FHA, Dhoedt B, De Turck F, Fostier J, Demeester P, Vanrolleghem PA (2012) Online execution time prediction for computationally intensive applications with periodic progress updates. J Supercomput 62(2):768\u2013786","journal-title":"J Supercomput"},{"key":"3417_CR111","doi-asserted-by":"publisher","unstructured":"Jayakumar A, Murali P, Vadhiyar S (2015) Matching application signatures for performance predictions using a single execution. In: 2015 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp 1161\u20131170. https:\/\/doi.org\/10.1109\/IPDPS.2015.20","DOI":"10.1109\/IPDPS.2015.20"},{"key":"3417_CR112","doi-asserted-by":"publisher","first-page":"241","DOI":"10.14311\/NNW.2015.25.013","volume":"25","author":"MF Akay","year":"2015","unstructured":"Akay MF, Aci CI, Abut F (2015) Predicting the performance measures of a 2-dimensional message passing multiprocessor architecture by using machine learning methods. Neural Netw World 25:241\u2013265","journal-title":"Neural Netw World"},{"key":"3417_CR113","doi-asserted-by":"crossref","unstructured":"Amar\u00eds M, de Camargo RY, Dyab M, Goldman A, Trystram D (2016) A comparison of GPU execution time prediction using machine learning and analytical modeling. In: 2016 IEEE 15th International Symposium on Network Computing and Applications (NCA), pp 326\u2013333","DOI":"10.1109\/NCA.2016.7778637"},{"issue":"7","key":"3417_CR114","doi-asserted-by":"publisher","first-page":"1800","DOI":"10.1109\/TPDS.2014.2333526","volume":"26","author":"TT Dao","year":"2015","unstructured":"Dao TT, Kim J, Seo S, Egger B, Lee J (2015) A performance model for GPUs with caches. IEEE Trans Parallel Distrib Syst 26(7):1800\u20131813","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3417_CR115","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s13042-016-0571-6","volume":"8","author":"T Doan","year":"2017","unstructured":"Doan T, Kalita J (2017) Predicting run time of classification algorithms using meta-learning. Int J Mach Learn Cybern 8:1929\u20131943","journal-title":"Int J Mach Learn Cybern"},{"issue":"5","key":"3417_CR116","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1016\/j.future.2009.05.004","volume":"26","author":"E Dodonov","year":"2010","unstructured":"Dodonov E, de Mello RF (2010) A novel approach for distributed application scheduling based on prediction of communication events. Future Gener Comput Syst 26(5):740\u2013752. https:\/\/doi.org\/10.1016\/j.future.2009.05.004","journal-title":"Future Gener Comput Syst"},{"key":"3417_CR117","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.artint.2013.10.003","volume":"206","author":"F Hutter","year":"2014","unstructured":"Hutter F, Xu L, Hoos HH, Leyton-Brown K (2014) Algorithm runtime prediction: methods & evaluation. Artif Intell 206:79\u2013111. https:\/\/doi.org\/10.1016\/j.artint.2013.10.003","journal-title":"Artif Intell"},{"key":"3417_CR118","doi-asserted-by":"publisher","unstructured":"Ipek E, de Supinski BR, Schulz M, McKee SA (2005) An approach to performance prediction for parallel applications. In: Cunha JC, Medeiros PD (eds) Euro-par 2005 parallel processing, volume 3648 of lecture notes in computer science. Springer, Berlin, pp 196\u2013205. https:\/\/doi.org\/10.1007\/11549468_24","DOI":"10.1007\/11549468_24"},{"key":"3417_CR119","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.sysarc.2009.09.004","volume":"55","author":"B Li","year":"2009","unstructured":"Li B, Peng L, Ramadass B (2009) Accurate and efficient processor performance prediction via regression tree based modeling. J Syst Archit 55:457\u2013467. https:\/\/doi.org\/10.1016\/j.sysarc.2009.09.004","journal-title":"J Syst Archit"},{"key":"3417_CR120","doi-asserted-by":"crossref","unstructured":"Ling Y, Liu F, Qiu Y, Zhao J (2016) Prediction of total execution time for MapReduce applications. In: 2016 Sixth International Conference on Information Science and Technology (ICIST), pp 341\u2013345","DOI":"10.1109\/ICIST.2016.7483435"},{"issue":"1\u20132","key":"3417_CR121","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.sysarc.2007.06.005","volume":"54","author":"MS Oyamada","year":"2008","unstructured":"Oyamada MS, Zschornack F, Wagner FR (2008) Applying neural networks to performance estimation of embedded software. J Syst Archit 54(1\u20132):224\u2013240. https:\/\/doi.org\/10.1016\/j.sysarc.2007.06.005","journal-title":"J Syst Archit"},{"key":"3417_CR122","doi-asserted-by":"publisher","unstructured":"Phinjaroenphan P, Bevinakoppa S, Zeephongsekul P (2005) A method for estimating the execution time of a parallel task on a grid node. In: Sloot PMA, Hoekstra AG, Priol T, Reinefeld A, Bubak M (eds) Advances in grid computing\u2014EGC 2005, volume 3470 of lecture notes in computer science. Springer, Berlin, pp 226\u2013236. https:\/\/doi.org\/10.1007\/11508380_24","DOI":"10.1007\/11508380_24"},{"issue":"1","key":"3417_CR123","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10723-005-9017-1","volume":"4","author":"H Prem","year":"2006","unstructured":"Prem H, Raghavan NRS (2006) A support vector machine based approach for forecasting of network weather services. J Grid Comput 4(1):89\u2013114. https:\/\/doi.org\/10.1007\/s10723-005-9017-1","journal-title":"J Grid Comput"},{"key":"3417_CR124","doi-asserted-by":"publisher","unstructured":"Smith W (2007) Prediction services for distributed computing. In: IEEE International Parallel and Distributed Processing Symposium, 2007. IPDPS 2007, pp 1\u201310. https:\/\/doi.org\/10.1109\/IPDPS.2007.370276","DOI":"10.1109\/IPDPS.2007.370276"},{"issue":"5","key":"3417_CR125","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/TC.2020.2964767","volume":"69","author":"J Sun","year":"2020","unstructured":"Sun J, Sun G, Zhan S, Zhang J, Chen Y (2020) Automated performance modeling of HPC applications using machine learning. IEEE Trans Comput 69(5):749\u2013763","journal-title":"IEEE Trans Comput"},{"key":"3417_CR126","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1007\/s10586-016-0707-1","volume":"20","author":"W Zhang","year":"2016","unstructured":"Zhang W, Hao M, Snir M (2016) Predicting HPC parallel program performance based on LLVM compiler. Clust Comput 20:1179\u20131192","journal-title":"Clust Comput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03417-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03417-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03417-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T12:18:25Z","timestamp":1668687505000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03417-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,10]]},"references-count":126,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["3417"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03417-5","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,10]]},"assertion":[{"value":"10 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}