Reducing the memory usage of Lattice-Boltzmann schemes with a DWT-based compression

Autor: Flint, Clément, Helluy, Philippe

This paper presents a new solution to address the challenge of increasing memory usage in high-performance computing simulations of Lattice-Bolzmann or Finite-Volume schemes.Our approach utilises a lossy compression scheme based on the Discrete Wavel

Externí odkaz: http://arxiv.org/abs/2302.09883

Parallelization of the Lattice-Boltzmann schemes using the task-based method

Autor: Flint, Clément, Bramas, Berenger, Genaud, Stephane, Helluy, Philippe

Publikováno v: COMPAS 2022-Conférence francophone d'informatique en Parallélisme, Architecture et Système
COMPAS 2022-Conférence francophone d'informatique en Parallélisme, Architecture et Système, Jul 2022, Amiens, France

National audience; The popularization of graphic processing units (GPUs) has led to their extensive use in highperformance numerical simulations. The Lattice Boltzmann Methodology (LBM) is a general framework for constructing efficient numerical flui

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6f48264767253192db021f29a9efa5f1
https://inria.hal.science/hal-03763577/file/ComPAS2022_paper_43-2.pdf

Finding new heuristics for automated task prioritizing in heterogeneous computing

Autor: Flint, Clément, Bramas, Bérenger

In many sciences, processing costly computations has become frequent and the execution time of an application is often viewed as a bottleneck. High-Performance Computing is a growing area of interest whose role is to reduce the execution time of thes

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f11ace5f441e15a0c0c1a1cc5ea6db2b
https://hal.inria.fr/hal-02993015