Navier-stokes on programmable graphics hardware using SMAC

Carlos Eduardo Scheidegger, João Luiz Dihl Comba, Rudnei Dias Da Cunha

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Modern programmable graphics hardware offers sufficient computing power to suggest the implementation of traditional algorithms on the graphics processor. This paper describes a complete implementation of a standard technique to solve the incompressible Navier-Stokes fluid equations running entirely on the GPU: the SMAC (Simplified Marker And Cell) method. This method is widely used in engineering applications. The described implementation works with general rectangular domains, with or without obstacles, and with a variety of boundary conditions. Furthermore, we show that our implementation is about sixteen times faster than a reference CPU implementation running on similar cost hardware. Finally, we discuss simple extensions to the method to deal with more general situations, such as free boundary-value problems and three-dimensional domains.

Original languageEnglish (US)
Title of host publicationBrazilian Symposium of Computer Graphic and Image Processing
EditorsA.A. Araujo, J.L.D. Comba, I. Navazo, A.A. Souza
Pages300-307
Number of pages8
StatePublished - 2004
Externally publishedYes
EventProceedings - XVII Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2004. And II Ibero-American Symposium on Computer Graphics, SIACG 2004 - Curitiba, Brazil
Duration: Oct 17 2004Oct 20 2004

Other

OtherProceedings - XVII Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2004. And II Ibero-American Symposium on Computer Graphics, SIACG 2004
CountryBrazil
CityCuritiba
Period10/17/0410/20/04

Fingerprint

Computer hardware
Boundary value problems
Program processors
Boundary conditions
Hardware
Fluids
Costs
Graphics processing unit

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Scheidegger, C. E., Comba, J. L. D., & Da Cunha, R. D. (2004). Navier-stokes on programmable graphics hardware using SMAC. In A. A. Araujo, J. L. D. Comba, I. Navazo, & A. A. Souza (Eds.), Brazilian Symposium of Computer Graphic and Image Processing (pp. 300-307)

Navier-stokes on programmable graphics hardware using SMAC. / Scheidegger, Carlos Eduardo; Comba, João Luiz Dihl; Da Cunha, Rudnei Dias.

Brazilian Symposium of Computer Graphic and Image Processing. ed. / A.A. Araujo; J.L.D. Comba; I. Navazo; A.A. Souza. 2004. p. 300-307.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Scheidegger, CE, Comba, JLD & Da Cunha, RD 2004, Navier-stokes on programmable graphics hardware using SMAC. in AA Araujo, JLD Comba, I Navazo & AA Souza (eds), Brazilian Symposium of Computer Graphic and Image Processing. pp. 300-307, Proceedings - XVII Brazilian Symposium on Computer Graphics and Image Processing, SIBGRAPI 2004. And II Ibero-American Symposium on Computer Graphics, SIACG 2004, Curitiba, Brazil, 10/17/04.
Scheidegger CE, Comba JLD, Da Cunha RD. Navier-stokes on programmable graphics hardware using SMAC. In Araujo AA, Comba JLD, Navazo I, Souza AA, editors, Brazilian Symposium of Computer Graphic and Image Processing. 2004. p. 300-307
Scheidegger, Carlos Eduardo ; Comba, João Luiz Dihl ; Da Cunha, Rudnei Dias. / Navier-stokes on programmable graphics hardware using SMAC. Brazilian Symposium of Computer Graphic and Image Processing. editor / A.A. Araujo ; J.L.D. Comba ; I. Navazo ; A.A. Souza. 2004. pp. 300-307
@inproceedings{be513ea412a64ebea74df4327118c41a,
title = "Navier-stokes on programmable graphics hardware using SMAC",
abstract = "Modern programmable graphics hardware offers sufficient computing power to suggest the implementation of traditional algorithms on the graphics processor. This paper describes a complete implementation of a standard technique to solve the incompressible Navier-Stokes fluid equations running entirely on the GPU: the SMAC (Simplified Marker And Cell) method. This method is widely used in engineering applications. The described implementation works with general rectangular domains, with or without obstacles, and with a variety of boundary conditions. Furthermore, we show that our implementation is about sixteen times faster than a reference CPU implementation running on similar cost hardware. Finally, we discuss simple extensions to the method to deal with more general situations, such as free boundary-value problems and three-dimensional domains.",
author = "Scheidegger, {Carlos Eduardo} and Comba, {Jo{\~a}o Luiz Dihl} and {Da Cunha}, {Rudnei Dias}",
year = "2004",
language = "English (US)",
pages = "300--307",
editor = "A.A. Araujo and J.L.D. Comba and I. Navazo and A.A. Souza",
booktitle = "Brazilian Symposium of Computer Graphic and Image Processing",

}

TY - GEN

T1 - Navier-stokes on programmable graphics hardware using SMAC

AU - Scheidegger, Carlos Eduardo

AU - Comba, João Luiz Dihl

AU - Da Cunha, Rudnei Dias

PY - 2004

Y1 - 2004

N2 - Modern programmable graphics hardware offers sufficient computing power to suggest the implementation of traditional algorithms on the graphics processor. This paper describes a complete implementation of a standard technique to solve the incompressible Navier-Stokes fluid equations running entirely on the GPU: the SMAC (Simplified Marker And Cell) method. This method is widely used in engineering applications. The described implementation works with general rectangular domains, with or without obstacles, and with a variety of boundary conditions. Furthermore, we show that our implementation is about sixteen times faster than a reference CPU implementation running on similar cost hardware. Finally, we discuss simple extensions to the method to deal with more general situations, such as free boundary-value problems and three-dimensional domains.

AB - Modern programmable graphics hardware offers sufficient computing power to suggest the implementation of traditional algorithms on the graphics processor. This paper describes a complete implementation of a standard technique to solve the incompressible Navier-Stokes fluid equations running entirely on the GPU: the SMAC (Simplified Marker And Cell) method. This method is widely used in engineering applications. The described implementation works with general rectangular domains, with or without obstacles, and with a variety of boundary conditions. Furthermore, we show that our implementation is about sixteen times faster than a reference CPU implementation running on similar cost hardware. Finally, we discuss simple extensions to the method to deal with more general situations, such as free boundary-value problems and three-dimensional domains.

UR - http://www.scopus.com/inward/record.url?scp=16244378033&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=16244378033&partnerID=8YFLogxK

M3 - Conference contribution

SP - 300

EP - 307

BT - Brazilian Symposium of Computer Graphic and Image Processing

A2 - Araujo, A.A.

A2 - Comba, J.L.D.

A2 - Navazo, I.

A2 - Souza, A.A.

ER -