Performance Modeling of MPI Applications Using Model Selection Techniques

Martínez, D.; Dominguez, Jessica A.; Pena, Tomás F.; Rivera, Francisco F.; Blanco, Vicente

doi:10.1109/pdp.2010.78

Cited by 6 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, broadcast algorithms were considered in this paper. A comprehensive and rigorous analysis of these algorithms has been performed, which improves the preliminary results presented in [8].This paper is organized as follows. In Section 2, the theoretical basis of the modeling method is introduced.…”

mentioning

confidence: 89%

“…This criterion, widely used in the fields of biology and econometrics, is an objective tool that ranks the models according to their suitability for describing the experimental data. In , a preliminary version of this modeling method was introduced, which was loosely integrated on the Tools for Instrumentation and Analysis (TIA) modeling framework . The present work formalizes the description of the method, including new features such as a renewed procedure to interact with the user and its full integration on the TIA framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling the performance of parallel applications using model selection techniques

Martínez

Blanco

Dominguez

et al. 2013

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYNowadays, parallel architectures are changing so fast that there is a need for scalable and efficient tools to analyze and predict the performance of parallel applications. Analytical models are proved to be a useful approximation for characterizing parallel algorithms, but developing accurate analytical models is a hard issue, and, in general, they provide coarse performance predictions due to their intrinsic lack of accuracy. In this paper, we describe in detail the Tools for Instrumentation and Analysis (TIA) framework, an easy-touse tool that automatically obtains accurate performance models by means of analytical expressions. This framework automatizes most of its internal tasks, reducing opportunities for human error, and it only requires the user to focus on the metrics and execution parameters that might influence the performance, those that should be considered in the modeling process. Its main advantage over other tools is that TIA uses model selection techniques that allow the automation of the modeling process. As a case of study, the use of TIA to obtain analytical models of different implementations of the broadcast collective communication in a cluster of multicores is shown. The results obtained by TIA are evaluated and compared with theoretical approaches based on the LogGP model.

show abstract

mentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Modeling the performance of parallel applications using model selection techniques

Martínez

Blanco

Dominguez

et al. 2013

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…As an example, let's consider a linear implementation of the broadcast collective communication described in a previous work [3]. In this case, the set of candidate models was generated by WL = {n s }{m s }{P, log 2 P , log 2 P }, where n s is the number of segments of a message, m s the size of each segment and P the number of processes.…”

Section: Genetic Algorithm For Model Selectionmentioning

confidence: 99%

“…A model selection method based on the AIC has been implemented in this stage [3]. This method uses a finite set of candidate models which are automatically generated from information provided by the user.…”

Section: Introductionmentioning

confidence: 99%

Model Selection to Characterize Performance Using Genetic Algorithms

Martínez

Dominguez

Pena

et al. 2012

2012 IEEE 10th International Symposium on Parallel and Distributed Processing With Applications

View full text Add to dashboard Cite

The TIA modeling framework provides analytical models of the performance of parallel applications. The resulting models are obtained using model selection techniques and are accurate enough for various purposes. Its main drawback is that the completion time depends on the number of candidate models and, in some situations, it becomes critical. In this work, a genetic algorithm is proposed for reducing the time for searching of the best candidate model. The use of this genetic algorithm to obtain the performance model of the linear implementation of the broadcast collective communication in a cluster of multicores is shown.

show abstract

“…In the second stage (analysis), the models are calculated by analyzing the performance information obtained from multiple executions of the instrumented code. The model selection methodology based on AIC has been implemented in the analysis stage [7], so that the data from the instrumentation stage can be used by the modeling process. This implementation provides the model with the lowest AIC score as the best model for future inferences, but also provides some statistical information to help the user to decide the suitability of the model.…”

Section: The Modeling Frameworkmentioning

confidence: 99%

Using accurate AIC-based performance models to improve the scheduling of parallel applications

et al. 2011

View full text Add to dashboard Cite

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.

show abstract

Performance Modeling of MPI Applications Using Model Selection Techniques

Cited by 6 publications

References 20 publications

Modeling the performance of parallel applications using model selection techniques

Modeling the performance of parallel applications using model selection techniques

Model Selection to Characterize Performance Using Genetic Algorithms

Using accurate AIC-based performance models to improve the scheduling of parallel applications

Contact Info

Product

Resources

About