Within the last decade, microprocessor development reached a point at which higher clock rates and more complex micro-architectures became less energy-efficient, such that power consumption and energy density were pushed beyond reasonable limits. As a consequence, the industry has shifted to more energy efficient multi-core designs, integrating multiple processing units (cores) on a single chip. The number of cores is expected to grow exponentially and future systems are expected to integrate thousands of processing units. In order to provide sufficient memory bandwidth in these systems, main memory is physically distributed over multiple memory controllers with non-uniform access to memory (NUMA). Past research has identified programming m...
Hybrid computing platforms equipped with accelerators are now commonplace in high performance comput...
The demand for large compute capabilities in scientific computing led to wide use and acceptance of ...
International audienceThe recent addition of data dependencies to the OpenMP 4.0 standard provides t...
Au milieu des années deux mille, le développement de microprocesseurs a atteint un point à partir du...
Nowadays the evolution of High Performance Computing follows the needs of numerical simulations.Thes...
International audienceDynamic task-parallel programming models are popular on shared-memory systems,...
Anticipating the behavior of applications, studying, and designing algorithms are some of the most i...
International audienceWe present a joint scheduling and memory allocation algorithm for efficient ex...
Modern multicore systems are based on a Non-Uniform Memory Access (NUMA) design. In a NUMA system, c...
Multi-core platforms with non-uniform memory access (NUMA) design are now a common resource in High ...
Hardware accelerators, such as GPUs, now provide a large part of the computational power used for sc...
Processors with multiple sockets or chiplets are becoming more conventional. These kinds of processo...
International audienceExploiting the full computational power of current hierarchical multiprocessor...
International audienceOpenMP 4.0 introduced dependent tasks, which give the programmer a way to expr...
The task parallel programming model allows programmers to express concurrency at a high level of abs...
Hybrid computing platforms equipped with accelerators are now commonplace in high performance comput...
The demand for large compute capabilities in scientific computing led to wide use and acceptance of ...
International audienceThe recent addition of data dependencies to the OpenMP 4.0 standard provides t...
Au milieu des années deux mille, le développement de microprocesseurs a atteint un point à partir du...
Nowadays the evolution of High Performance Computing follows the needs of numerical simulations.Thes...
International audienceDynamic task-parallel programming models are popular on shared-memory systems,...
Anticipating the behavior of applications, studying, and designing algorithms are some of the most i...
International audienceWe present a joint scheduling and memory allocation algorithm for efficient ex...
Modern multicore systems are based on a Non-Uniform Memory Access (NUMA) design. In a NUMA system, c...
Multi-core platforms with non-uniform memory access (NUMA) design are now a common resource in High ...
Hardware accelerators, such as GPUs, now provide a large part of the computational power used for sc...
Processors with multiple sockets or chiplets are becoming more conventional. These kinds of processo...
International audienceExploiting the full computational power of current hierarchical multiprocessor...
International audienceOpenMP 4.0 introduced dependent tasks, which give the programmer a way to expr...
The task parallel programming model allows programmers to express concurrency at a high level of abs...
Hybrid computing platforms equipped with accelerators are now commonplace in high performance comput...
The demand for large compute capabilities in scientific computing led to wide use and acceptance of ...
International audienceThe recent addition of data dependencies to the OpenMP 4.0 standard provides t...