The paper extends the framework of linear loop transformations adding a new nonlinear step at the transformation process. The current framework of linear loop transformation cannot identify a significant fraction of parallelism. For this reason, we present a method to complement it with some basic transformations in order to extract the maximum loop parallelism in perfect nested loops with tight recurrences in the dependence graph. The parallelizing algorithm solves the important problem of deciding the set of transformations to apply in order to maximize the degree of parallelism, the number of parallel loops within a loop nest, and presents a way of generating efficient transformed code that exploits coarse grain parallelism on a MIMD system ; Peer Reviewed ; Postprint (published version)


    Zugriff

    Download


    Exportieren, teilen und zitieren



    PARALLELIZATION METHOD, PARALLELIZATION TOOL, AND MULTICORE MICROCOMPUTER

    MINEDA KENICHI | Europäisches Patentamt | 2019

    Freier Zugriff

    Tasking Framework: Parallelization of Computations in Onboard Control Systems

    Maibaum, Olaf / Lüdtke, Daniel / Gerndt, Andreas | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2013

    Freier Zugriff

    PARALLELIZATION METHOD, PARALLELIZATION TOOL AND ON-VEHICLE CONTROL DEVICE

    MINEDA KENICHI | Europäisches Patentamt | 2018

    Freier Zugriff

    SOLVCON: A PYTHON-BASED CFD SOFTWARE FRAMEWORK FOR HYBRID PARALLELIZATION

    Chen, Y.-Y. / Bilyeu, D. / Yang, L. et al. | British Library Conference Proceedings | 2011


    SOLVCON: A Python-Based CFD Software Framework for Hybrid Parallelization

    Chen, Yung-Yu / Bilyeu, David / Yang, Lixiang et al. | AIAA | 2011