Abstract

Peridynamic (PD) codes, which are written by using any programming language, e.g., C, C++, FORTRAN, or Java, can be run in any available computing facility. This can be a desktop/laptop computer or a high performance computing (HPC) facility. Nowadays, desktops/laptops include many central processing units (CPUs) and relatedly many cores in their architectures. Moreover, graphical processing units (GPUs) of computers have been improved above and beyond the expectations. Either one of them or both of them can be benefited in order to solve large and complicated problems in personal desktops/laptops. This chapter presents how it is possible to improve PD codes and make them efficient for large-scale problems with the help of parallel programming procedures. Moreover, how simple modifications with very basic knowledge of parallel programming skills can lead to significant increase in our calculation speeds is demonstrated. Specifically, CPU- and GPU-based approaches are explained for parallelizing PD codes.
Original languageEnglish
Title of host publicationPeridynamic Modeling, Numerical Techniques, and Applications
EditorsErkan Oterkus, Selda Oterkus, Erdogan Madenci
Place of PublicationAmsterdam, Netherlands
Chapter19
Pages403-417
Number of pages15
DOIs
Publication statusPublished - 30 Apr 2021

Publication series

NameA volume in Elsevier Series in Mechanics of Advanced Materials

Keywords

  • central processing units
  • graphical processing units
  • high performance computing
  • parallel programming
  • peridynamics

Fingerprint Dive into the research topics of 'Application of high-performance computing for peridynamics'. Together they form a unique fingerprint.

Cite this