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

With the introduction of advanced heterogeneous computing architectures basedon GPU accelerators, large-scale production codes have had to rethink theirnumerical algorithms and incorporate new programming models and memorymanagement strategies in order to run efficiently on the latest supercomputers.In this work we discuss our co-design strategy to address these challenges andachieve performance and portability with MARBL, a next-generation multi-physicscode in development at Lawrence Livermore National Laboratory. We present atwo-fold approach, wherein new hardware is used to motivate both new algorithmsand new abstraction layers, resulting in a single source application codesuitable for a variety of platforms. Focusing on MARBL's ALE hydrodynamicspackage, we demonstrate scalability on different platforms and highlight thatmany of our innovations have been contributed back to open-source softwarelibraries, such as MFEM (finite element algorithms) and RAJA (kernelabstractions).

Matrix-free approaches for GPU acceleration of a high-order finite element hydrodynamics application using MFEM, Umpire, and RAJA