Practical CFD simulations on programmable graphics hardware using SMAC

Carlos Eduardo Scheidegger, João L D Comba, Rudnei D. Da Cunha

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

The explosive growth in integration technology and the parallel nature of rasterization-based graphics APIs (Application Programming Interface) changed the panorama of consumer-level graphics: today, GPUs (Graphics Processing Units) are cheap, fast and ubiquitous. We show how to harness the computational power of GPUs and solve the incompressible Navier-Stokes fluid equations significantly faster (more than one order of magnitude in average) than on CPU solvers of comparable cost. While past approaches typically used Stam's implicit solver, we use a variation of SMAC (Simplified Marker and Cell). SMAC is widely used in engineering applications, where experimental reproducibility is essential. Thus, we show that the GPU is a viable and affordable processor for scientific applications. Our solver works with general rectangular domains (possibly with obstacles), implements a variety of boundary conditions and incorporates energy transport through the traditional Boussinesq approximation. Finally, we discuss the implications of our solver in light of future GPU features, and possible extensions such as three-dimensional domains and free-boundary problems.

Original languageEnglish (US)
Pages (from-to)715-728
Number of pages14
JournalComputer Graphics Forum
Volume24
Issue number4
DOIs
StatePublished - Dec 2005
Externally publishedYes

Fingerprint

Computational fluid dynamics
Hardware
Application programming interfaces (API)
Program processors
Boundary conditions
Fluids
Graphics processing unit
Costs

Keywords

  • Computational fluid dynamics
  • Graphics hardware

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Practical CFD simulations on programmable graphics hardware using SMAC. / Scheidegger, Carlos Eduardo; Comba, João L D; Da Cunha, Rudnei D.

In: Computer Graphics Forum, Vol. 24, No. 4, 12.2005, p. 715-728.

Research output: Contribution to journalArticle

Scheidegger, Carlos Eduardo ; Comba, João L D ; Da Cunha, Rudnei D. / Practical CFD simulations on programmable graphics hardware using SMAC. In: Computer Graphics Forum. 2005 ; Vol. 24, No. 4. pp. 715-728.
@article{d407e75a592c4e828292e7d6490ced38,
title = "Practical CFD simulations on programmable graphics hardware using SMAC",
abstract = "The explosive growth in integration technology and the parallel nature of rasterization-based graphics APIs (Application Programming Interface) changed the panorama of consumer-level graphics: today, GPUs (Graphics Processing Units) are cheap, fast and ubiquitous. We show how to harness the computational power of GPUs and solve the incompressible Navier-Stokes fluid equations significantly faster (more than one order of magnitude in average) than on CPU solvers of comparable cost. While past approaches typically used Stam's implicit solver, we use a variation of SMAC (Simplified Marker and Cell). SMAC is widely used in engineering applications, where experimental reproducibility is essential. Thus, we show that the GPU is a viable and affordable processor for scientific applications. Our solver works with general rectangular domains (possibly with obstacles), implements a variety of boundary conditions and incorporates energy transport through the traditional Boussinesq approximation. Finally, we discuss the implications of our solver in light of future GPU features, and possible extensions such as three-dimensional domains and free-boundary problems.",
keywords = "Computational fluid dynamics, Graphics hardware",
author = "Scheidegger, {Carlos Eduardo} and Comba, {Jo{\~a}o L D} and {Da Cunha}, {Rudnei D.}",
year = "2005",
month = "12",
doi = "10.1111/j.1467-8659.2005.00897.x",
language = "English (US)",
volume = "24",
pages = "715--728",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Practical CFD simulations on programmable graphics hardware using SMAC

AU - Scheidegger, Carlos Eduardo

AU - Comba, João L D

AU - Da Cunha, Rudnei D.

PY - 2005/12

Y1 - 2005/12

N2 - The explosive growth in integration technology and the parallel nature of rasterization-based graphics APIs (Application Programming Interface) changed the panorama of consumer-level graphics: today, GPUs (Graphics Processing Units) are cheap, fast and ubiquitous. We show how to harness the computational power of GPUs and solve the incompressible Navier-Stokes fluid equations significantly faster (more than one order of magnitude in average) than on CPU solvers of comparable cost. While past approaches typically used Stam's implicit solver, we use a variation of SMAC (Simplified Marker and Cell). SMAC is widely used in engineering applications, where experimental reproducibility is essential. Thus, we show that the GPU is a viable and affordable processor for scientific applications. Our solver works with general rectangular domains (possibly with obstacles), implements a variety of boundary conditions and incorporates energy transport through the traditional Boussinesq approximation. Finally, we discuss the implications of our solver in light of future GPU features, and possible extensions such as three-dimensional domains and free-boundary problems.

AB - The explosive growth in integration technology and the parallel nature of rasterization-based graphics APIs (Application Programming Interface) changed the panorama of consumer-level graphics: today, GPUs (Graphics Processing Units) are cheap, fast and ubiquitous. We show how to harness the computational power of GPUs and solve the incompressible Navier-Stokes fluid equations significantly faster (more than one order of magnitude in average) than on CPU solvers of comparable cost. While past approaches typically used Stam's implicit solver, we use a variation of SMAC (Simplified Marker and Cell). SMAC is widely used in engineering applications, where experimental reproducibility is essential. Thus, we show that the GPU is a viable and affordable processor for scientific applications. Our solver works with general rectangular domains (possibly with obstacles), implements a variety of boundary conditions and incorporates energy transport through the traditional Boussinesq approximation. Finally, we discuss the implications of our solver in light of future GPU features, and possible extensions such as three-dimensional domains and free-boundary problems.

KW - Computational fluid dynamics

KW - Graphics hardware

UR - http://www.scopus.com/inward/record.url?scp=33745187381&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745187381&partnerID=8YFLogxK

U2 - 10.1111/j.1467-8659.2005.00897.x

DO - 10.1111/j.1467-8659.2005.00897.x

M3 - Article

AN - SCOPUS:33745187381

VL - 24

SP - 715

EP - 728

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

IS - 4

ER -