English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A novel parallelization paradigm has been developed for multi-GPUarchitectures. Classical multi-GPU parallelization for SPH rely on domaindecomposition. In our approach each particle can be assigned to a GPUindependently of its position in space. This ensures a kind of natural loadbalancing because the number of particles per GPU remains constant. The dataexchange domain is no more a surface as in the classical approach or inmesh-based method, but it is a volume which is growing as mixing occurs in timebetween the particles assigned to different GPUs. This growth must be preventedbecause the efficiency in terms of computation time and memory consumption israpidly dropping with the mixing. A simple heuristic is suggested toperiodically detect particles to swap between GPUs in order to keep theexchange volume close to a surface. The final decomposition is much alike adomain decomposition and can be applied to any geometry. We developed thisapproach within the framework of the industrial code IMPETUS Solver using theGamma-SPH-ALE method. Industrial applications in the space and military fieldsare presented. They demonstrate the relevance of the approach developed in anindustrial context and for complex applications.

A novel multi-GPU parallelization paradigm for SPH applied to solid mechanics in complex industrial applications