Most components of High Performance Computing systems, either hardware or software, come with many tunable parameters and their parametrization can have a significant impact on their performance. For optimal performance, the most adapted parametrization for each application running on the cluster must be determined and used. However, this parametrization is difficult to find because of the complexity of the relationship between each component and the lack of insight on the system’s behavior.In this thesis, we remove the complex task of tuning the system manually or through theoretical models, by exploring auto-tuning methods relying on black-box optimization to find the system’s optimal parameters. We provide a comprehensive comparison of t...
In high-performance computing, excellent node-level performance is required for the efficient use of...
Les métaheuristiques sont une famille d'algorithmes stochastiques destinés à résoudre des problèmes ...
To solve discrete optimization problems of black box type, many stochastic algorithms such as evolut...
Most components of High Performance Computing systems, either hardware or software, come with many t...
La plupart des composants des systèmes à Haute Performance, qu'ils soient matériels ou logiciels, so...
La fin de la loi de Moore et de la loi de Dennard entraînent une augmentation de la complexité du ma...
The end of Moore's Law and the breakdown of Dennard's scaling mean thatincreasing hardware ...
MPI libraries are widely used in applications of high performance computing. Yet, effective tuning o...
MPI libraries are widely used in applications of high performance computing. Yet, effective tuning o...
This PhD thesis focuses on the automated algorithm configuration that aims at finding the best param...
International audienceFinely tuning MPI applications and understanding the influence of keyparameter...
International audienceHigh Performance Computing platforms are made to answer the need of huge compu...
Recent years have witnessed phenomenal growth in the application, and capabilities of Graphical Proc...
Due to their complexity, modern systems expose many con-figuration parameters which users must ...
Un problème d'optimisation continue peut se définir ainsi : étant donné une fonction objectif de R à...
In high-performance computing, excellent node-level performance is required for the efficient use of...
Les métaheuristiques sont une famille d'algorithmes stochastiques destinés à résoudre des problèmes ...
To solve discrete optimization problems of black box type, many stochastic algorithms such as evolut...
Most components of High Performance Computing systems, either hardware or software, come with many t...
La plupart des composants des systèmes à Haute Performance, qu'ils soient matériels ou logiciels, so...
La fin de la loi de Moore et de la loi de Dennard entraînent une augmentation de la complexité du ma...
The end of Moore's Law and the breakdown of Dennard's scaling mean thatincreasing hardware ...
MPI libraries are widely used in applications of high performance computing. Yet, effective tuning o...
MPI libraries are widely used in applications of high performance computing. Yet, effective tuning o...
This PhD thesis focuses on the automated algorithm configuration that aims at finding the best param...
International audienceFinely tuning MPI applications and understanding the influence of keyparameter...
International audienceHigh Performance Computing platforms are made to answer the need of huge compu...
Recent years have witnessed phenomenal growth in the application, and capabilities of Graphical Proc...
Due to their complexity, modern systems expose many con-figuration parameters which users must ...
Un problème d'optimisation continue peut se définir ainsi : étant donné une fonction objectif de R à...
In high-performance computing, excellent node-level performance is required for the efficient use of...
Les métaheuristiques sont une famille d'algorithmes stochastiques destinés à résoudre des problèmes ...
To solve discrete optimization problems of black box type, many stochastic algorithms such as evolut...