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

doi:10.1007/s10586-013-0329-9

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

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

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.

Original language	English (US)
Pages (from-to)	243-254
Number of pages	12
Journal	Cluster Computing
Volume	17
Issue number	2
DOIs	https://doi.org/10.1007/s10586-013-0329-9
State	Published - Jan 2014

Bibliographical note

Funding Information:
Acknowledgements This work has received financial support of Agencia Nacional de Promoción Científica y Tecnológica (ANPCyT, Argentina, grants PICT-1141/2007, PICT-0270/2008, PICT-2492/ 2010), Universidad Nacional del Litoral (UNL, Argentina, grants CAI+D 2009-65/334, CAI+D-2009-III-4-2) y European Research Council (ERC) Advanced Grant, Real Time Computational Mechanics Techniques for Multi-Fluid Problems (REALTIME, Reference: ERC-2009-AdG, Dir: Dr. Sergio Idelsohn).

Keywords

BFECC
CUDA
GPGPU
Level-Set
Navier-Stokes
Semi-Lagrangian

ASJC Scopus subject areas

Software
Computer Networks and Communications

Access to Document

10.1007/s10586-013-0329-9

Cite this

@article{67b7499f43df4909b791cd1c8abdf740,

title = "GPGPU implementation of the BFECC algorithm for pure advection equations",

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 = "BFECC, CUDA, GPGPU, Level-Set, Navier-Stokes, Semi-Lagrangian",

author = "Costarelli, {Santiago D.} and Storti, {Mario A.} and Paz, {Rodrigo R.} and Dalcin, {Lisandro D.} and Idelsohn, {Sergio R.}",

note = "Funding Information: Acknowledgements This work has received financial support of Agencia Nacional de Promoci{\'o}n Cient{\'i}fica y Tecnol{\'o}gica (ANPCyT, Argentina, grants PICT-1141/2007, PICT-0270/2008, PICT-2492/ 2010), Universidad Nacional del Litoral (UNL, Argentina, grants CAI+D 2009-65/334, CAI+D-2009-III-4-2) y European Research Council (ERC) Advanced Grant, Real Time Computational Mechanics Techniques for Multi-Fluid Problems (REALTIME, Reference: ERC-2009-AdG, Dir: Dr. Sergio Idelsohn).",

year = "2014",

month = jan,

doi = "10.1007/s10586-013-0329-9",

language = "English (US)",

volume = "17",

pages = "243--254",

journal = "Cluster Computing",

issn = "1386-7857",

publisher = "Kluwer Academic Publishers",

number = "2",

}

TY - JOUR

T1 - GPGPU implementation of the BFECC algorithm for pure advection equations

AU - Costarelli, Santiago D.

AU - Storti, Mario A.

AU - Paz, Rodrigo R.

AU - Dalcin, Lisandro D.

AU - Idelsohn, Sergio R.

N1 - Funding Information: Acknowledgements This work has received financial support of Agencia Nacional de Promoción Científica y Tecnológica (ANPCyT, Argentina, grants PICT-1141/2007, PICT-0270/2008, PICT-2492/ 2010), Universidad Nacional del Litoral (UNL, Argentina, grants CAI+D 2009-65/334, CAI+D-2009-III-4-2) y European Research Council (ERC) Advanced Grant, Real Time Computational Mechanics Techniques for Multi-Fluid Problems (REALTIME, Reference: ERC-2009-AdG, Dir: Dr. Sergio Idelsohn).

PY - 2014/1

Y1 - 2014/1

N2 - 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.

AB - 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.

KW - BFECC

KW - CUDA

KW - GPGPU

KW - Level-Set

KW - Navier-Stokes

KW - Semi-Lagrangian

UR - http://www.scopus.com/inward/record.url?scp=84901618496&partnerID=8YFLogxK

U2 - 10.1007/s10586-013-0329-9

DO - 10.1007/s10586-013-0329-9

M3 - Article

AN - SCOPUS:84901618496

SN - 1386-7857

VL - 17

SP - 243

EP - 254

JO - Cluster Computing

JF - Cluster Computing

IS - 2

ER -

GPGPU implementation of the BFECC algorithm for pure advection equations

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this