Structured Adaptive Mesh Refinement Adaptations to Retain Performance Portability With Increasing Heterogeneity

Autor:	Carsten Burstedde, Mohammed Wahib, Martin Berzins, Michael L. Norman, Anshu Dubey, Didem Unat, Konrad Hinsen
Rok vydání:	2021
Předmět:	Hardware architecture Software portability Hierarchy Memory management General Computer Science Parallel processing (DSP implementation) Adaptive mesh refinement Computer science Asynchronous communication Distributed computing General Engineering Data_CODINGANDINFORMATIONTHEORY Resolution (logic)
Zdroj:	Computing in Science & Engineering. 23:62-66
ISSN:	1558-366X 1521-9615
Popis:	Adaptive mesh refinement (AMR) is an important method that enables many mesh-based applications to run at effectively higher resolution within limited computing resources by allowing high resolution only where really needed. This advantage comes at a cost, however: greater complexity in the mesh management machinery and challenges with load distribution. With the current trend of increasing heterogeneity in hardware architecture, AMR presents an orthogonal axis of complexity. The usual techniques, such as asynchronous communication and hierarchy management for parallelism and memory that are necessary to obtain reasonable performance are very challenging to reason about with AMR. Different groups working with AMR are bringing different approaches to this challenge. Here, we examine the design choices of several AMR codes and also the degree to which demands placed on them by their users influence these choices.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::70b6a7afa827568cd9f8d096c3322d88 https://doi.org/10.1109/mcse.2021.3099603 Zobrazit plný text záznamu