Compilation for todays microprocessor and multi-processor architectures is facing new challenges. Dealing with parallel execution, optimizations become overly specific and complex to be left to the programmer. Traditionally devoted to numerical applications, automatic parallelization addresses new program models, including non-affine nests of loops, recursive calls and pointer-based data structures. Parallelism detection is based on precise analyses, gathering compile-time information about run-time program properties. This information enables transformations useful to parallelism extraction and parallel code generation. This thesis focuses on aggressive analysis and transformation techniques from an instancewise point of view, that is from...
(eng) In this paper, we survey loop parallelization algorithms, analyzing the dependence representat...
In this thesis, we introduce Rec2Poly, a framework for speculative rewriting of recursive programs a...
Depuis plusieurs années, le nombre de cœurs de calcul dans les processeurs ne cesse d'augmenter à ch...
Compilation for todays microprocessor and multi-processor architectures is facing new challenges. De...
La compilation traditionnelle est confrontée à de nombreux défis face aux besoins d'optimisations de...
The constant evolution of processors architectures, with superscalar, instruction-level parallelism,...
The goal of parallelizing, or restructuring, compilers is to detect and exploit parallelism in seque...
Depuis plusieurs années, le nombre de cœurs de calcul dans les processeurs ne cesse d'augmenter à ch...
Les processeurs multi-coeurs sont maintenant largement utilisés presque partout en informatique: ord...
Traditional compilation faces numerous challenges with program optimizations for parallel architectu...
Many automatic software parallelization systems have been proposed in the past decades, but most of ...
In this thesis, we introduce Rec2Poly, a framework for speculative rewriting of recursiveprograms as...
(eng) In this paper, we survey loop parallelization algorithms, analyzing the dependence representat...
In this thesis, we introduce Rec2Poly, a framework for speculative rewriting of recursive programs a...
Depuis plusieurs années, le nombre de cœurs de calcul dans les processeurs ne cesse d'augmenter à ch...
Compilation for todays microprocessor and multi-processor architectures is facing new challenges. De...
La compilation traditionnelle est confrontée à de nombreux défis face aux besoins d'optimisations de...
The constant evolution of processors architectures, with superscalar, instruction-level parallelism,...
The goal of parallelizing, or restructuring, compilers is to detect and exploit parallelism in seque...
Depuis plusieurs années, le nombre de cœurs de calcul dans les processeurs ne cesse d'augmenter à ch...
Les processeurs multi-coeurs sont maintenant largement utilisés presque partout en informatique: ord...
Traditional compilation faces numerous challenges with program optimizations for parallel architectu...
Many automatic software parallelization systems have been proposed in the past decades, but most of ...
In this thesis, we introduce Rec2Poly, a framework for speculative rewriting of recursiveprograms as...
(eng) In this paper, we survey loop parallelization algorithms, analyzing the dependence representat...
In this thesis, we introduce Rec2Poly, a framework for speculative rewriting of recursive programs a...
Depuis plusieurs années, le nombre de cœurs de calcul dans les processeurs ne cesse d'augmenter à ch...