Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.Cataloged from PDF version of thesis.Includes bibliographical references (pages 41-42).Program optimization often can and need to be decoupled from the programs innate logic. In various domains, program autotuners have been developed which can automatically search for optimal program configurations using established optimization methods. OpenTuner is a general-purpose autotuner which provides a flexible search domain representation and robust optimization techniques. This thesis extends Open-Tuner with the family of population-based stochastic optimization (PBSO) algorithms to boost OpenTuner's search capability on discret...
Application auto-tuning has produced excellent results in a wide range of computing domains. Yet ada...
Abstract. The increasing complexities of modern architectures require compilers to extensively apply...
The best-performing algorithms for many hard problems are highly parameterized. Selecting the best h...
Automatic tuning (auto-tuning) of software has emerged in recent years as a promising method that tr...
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Comp...
Program autotuning has been shown to achieve better or more portable performance in a number of doma...
AbstractEmpirical performance optimization of computer codes using autotuners has received significa...
Abstract—Autotuning systems intelligently navigate a search space of possible implementations of a c...
Abstract. Tuning stochastic local search algorithms for tackling large instances is difficult due to...
International audienceMetaheuristic methods have been demonstrated to be efficient tools to solve ha...
Due to their complexity, modern systems expose many con-figuration parameters which users must ...
This paper proposes uRace, a unified race algorithm for efficient offline parameter tuning of determ...
We develop an online optimisation framework for self tuning of computer systems. Towards this, we fi...
Most sensitivity analysis studies of optimization algorithm control parameters are restricted to a s...
gorithms. Search algorithms usually depend on several parameters (e.g., population size and crossove...
Application auto-tuning has produced excellent results in a wide range of computing domains. Yet ada...
Abstract. The increasing complexities of modern architectures require compilers to extensively apply...
The best-performing algorithms for many hard problems are highly parameterized. Selecting the best h...
Automatic tuning (auto-tuning) of software has emerged in recent years as a promising method that tr...
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Comp...
Program autotuning has been shown to achieve better or more portable performance in a number of doma...
AbstractEmpirical performance optimization of computer codes using autotuners has received significa...
Abstract—Autotuning systems intelligently navigate a search space of possible implementations of a c...
Abstract. Tuning stochastic local search algorithms for tackling large instances is difficult due to...
International audienceMetaheuristic methods have been demonstrated to be efficient tools to solve ha...
Due to their complexity, modern systems expose many con-figuration parameters which users must ...
This paper proposes uRace, a unified race algorithm for efficient offline parameter tuning of determ...
We develop an online optimisation framework for self tuning of computer systems. Towards this, we fi...
Most sensitivity analysis studies of optimization algorithm control parameters are restricted to a s...
gorithms. Search algorithms usually depend on several parameters (e.g., population size and crossove...
Application auto-tuning has produced excellent results in a wide range of computing domains. Yet ada...
Abstract. The increasing complexities of modern architectures require compilers to extensively apply...
The best-performing algorithms for many hard problems are highly parameterized. Selecting the best h...