Cluster Computing

, Volume 17, Issue 2, pp 243–254

GPGPU implementation of the BFECC algorithm for pure advection equations

  • Santiago D. Costarelli
  • Mario A. Storti
  • Rodrigo R. Paz
  • Lisandro D. Dalcin
  • Sergio R. Idelsohn
Article

DOI: 10.1007/s10586-013-0329-9

Cite this article as:
Costarelli, S.D., Storti, M.A., Paz, R.R. et al. Cluster Comput (2014) 17: 243. doi:10.1007/s10586-013-0329-9

Abstract

In the present work an implementation of the Back and Forth Error Compensation and Correction (BFECC) algorithm specially suited for running on General-Purpose Graphics Processing Units (GPGPUs) through Nvidia’s Compute Unified Device Architecture (CUDA) is analyzed in order to solve transient pure advection equations. The objective is to compare it to a previous explicit version used in a Navier-Stokes solver fully written in CUDA. It turns out that BFECC could be implemented with unconditional stable stability using Semi-Lagrangian time integration allowing larger time steps than Eulerian ones.

Keywords

GPGPUCUDABFECCSemi-LagrangianLevel-SetNavier-Stokes

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Santiago D. Costarelli
    • 1
  • Mario A. Storti
    • 1
  • Rodrigo R. Paz
    • 1
  • Lisandro D. Dalcin
    • 1
  • Sergio R. Idelsohn
    • 1
    • 2
    • 3
  1. 1.CIMECINTEC - Universidad Nacional del Litoral y CONICETSanta FeArgentina
  2. 2.Institució Catalana de Recerca i Estudis Avançats (ICREA)BarcelonaSpain
  3. 3.International Center for Numerical Methods in Engineering (CIMNE)Technical University of Catalonia (UPC)BarcelonaSpain