caa a22 4500 445851678 CHVBK 20180317145415.0 cr unu---uuuuu 170323e20111201xx s 000 0 eng 10.1007/s11227-011-0589-1 doi (NATIONALLICENCE)springer-10.1007/s11227-011-0589-1 Using accurate AIC-based performance models toimprove the scheduling of parallel applications [Elektronische Daten] [Diego Martínez, Julio Albín, Tomás Pena, José Cabaleiro, Francisco Rivera, Vicente Blanco] Predictions based on analytical performance models can be used on efficient scheduling policies in order to select adequate resources for an optimal execution in terms of throughput and response time. However, developing accurate analytical models of parallel applications is a hard issue. The TIA (Tools for Instrumenting and Analysis) modeling framework provides an easy to use modeling method for obtaining analytical models of MPI applications. This method is based on modeling selection techniques and, in particular, on Akaike's information criterion (AIC). In this paper, first the AIC-based performance model of the HPL benchmark is obtained using the TIA modeling framework. Then the use of this model for assessing the runtime estimation on different backfilling policies is analyzed in the GridSim simulator. The behavior of these simulations is compared with the equivalent simulations based on the theoretical model of the HPL provided by its developers. Springer Science+Business Media, LLC, 2011 Performance nationallicence Analytical models nationallicence Model selection nationallicence Backfilling schedulers nationallicence Martínez Diego Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut Albín Julio Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut Pena Tomás Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut Cabaleiro José Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut Rivera Francisco Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut Blanco Vicente Dept. Statistic and Computer Science, La Laguna University, 38271, La Laguna, Spain aut The Journal of Supercomputing Springer US; http://www.springer-ny.com 58/3(2011-12-01), 332-340 0920-8542 58:3<332 2011 58 11227 https://doi.org/10.1007/s11227-011-0589-1 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11227-011-0589-1 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Martínez Diego Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut NATIONALLICENCE 700 1- Albín Julio Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut NATIONALLICENCE 700 1- Pena Tomás Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut NATIONALLICENCE 700 1- Cabaleiro José Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut NATIONALLICENCE 700 1- Rivera Francisco Dept. of Electronic and Computer Science, University of Santiago de Compostela, 15782, Santiago de Compostela, Spain aut NATIONALLICENCE 700 1- Blanco Vicente Dept. Statistic and Computer Science, La Laguna University, 38271, La Laguna, Spain aut NATIONALLICENCE 773 0- The Journal of Supercomputing Springer US; http://www.springer-ny.com 58/3(2011-12-01), 332-340 0920-8542 58:3<332 2011 58 11227 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer