International audienceThe paper presents X-Kaapi, a compact runtime for multicore architec- tures that brings multi parallel paradigms (parallel independent loops, fork-join tasks and dataflow tasks) in a unified framework without performance penalty. Comparisons on independent loops with OpenMP and on dense linear algebra with QUARK/PLASMA confirm our design decisions. Applied to EUROPLEXUS, an industrial simulation code for fast transient dynamics, we show that X-Kaapi achieves high speedups on multicore architectures by efficiently parallelizing both independent loops and dataflow tasks.Ce rapport présente X-Kaapi, un support exécutif pour archi- tecture multi-cœur qui permet l'exploitation conjointe de plusieurs paradigmes de programmat...
The shared memory architecture of multicore CPUs provides HENP developers with the opportunity to re...
The emergence of accelerators as standard computing resources on supercomputers and the subsequent a...
Faced with nearly stagnant clock speed advances, chip manufacturers have turned to parallelism as th...
International audienceThe paper presents X-Kaapi, a compact runtime for multicore architec- tures th...
Abstract—The paper presents X-KAAPI, a compact runtime for multicore architectures that brings multi...
International audienceMost recent HPC platforms have heterogeneous nodes composed of multi-core CPUs...
International audienceThis paper presents preliminary performance comparisons of parallel applicatio...
International audienceIn this paper, we focus on a distributed and parallel programming paradigm for...
Scientific and industrial applications that need high computational performance to be used are alway...
In this thesis, we propose to study the issues of task parallelism with data dependencies on multico...
International audienceThe emergence of accelerators as standard computing resources on supercomputer...
High performance architectures are constantly evolving in order to deliver ever greater compute powe...
The growing need for computing is more and more challenging, especially in the embedded system world...
International audienceTo efficiently exploit high performance computing platforms, applications curr...
International audienceIn this paper we propose a parallelization of interactive physical simulations...
The shared memory architecture of multicore CPUs provides HENP developers with the opportunity to re...
The emergence of accelerators as standard computing resources on supercomputers and the subsequent a...
Faced with nearly stagnant clock speed advances, chip manufacturers have turned to parallelism as th...
International audienceThe paper presents X-Kaapi, a compact runtime for multicore architec- tures th...
Abstract—The paper presents X-KAAPI, a compact runtime for multicore architectures that brings multi...
International audienceMost recent HPC platforms have heterogeneous nodes composed of multi-core CPUs...
International audienceThis paper presents preliminary performance comparisons of parallel applicatio...
International audienceIn this paper, we focus on a distributed and parallel programming paradigm for...
Scientific and industrial applications that need high computational performance to be used are alway...
In this thesis, we propose to study the issues of task parallelism with data dependencies on multico...
International audienceThe emergence of accelerators as standard computing resources on supercomputer...
High performance architectures are constantly evolving in order to deliver ever greater compute powe...
The growing need for computing is more and more challenging, especially in the embedded system world...
International audienceTo efficiently exploit high performance computing platforms, applications curr...
International audienceIn this paper we propose a parallelization of interactive physical simulations...
The shared memory architecture of multicore CPUs provides HENP developers with the opportunity to re...
The emergence of accelerators as standard computing resources on supercomputers and the subsequent a...
Faced with nearly stagnant clock speed advances, chip manufacturers have turned to parallelism as th...