Open Access
Open access
Elsevier
Theoretical and Applied Mechanics Letters
,  volume 13 ,  issue 5 ,  pages 100474

An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform

Publication type: Journal Article
Publication date: 2023-09-01
Elsevier
scimago Q1
wos Q2
SJR: 0.598
CiteScore: 5.9
Impact factor: 3.3
ISSN: 20950349
Mechanical Engineering
Mechanics of Materials
Environmental Engineering
Biomedical Engineering
Civil and Structural Engineering
Computational Mechanics
Aerospace Engineering
Ocean Engineering
Abstract
A computational fluid dynamics (CFD) solver for a GPU/CPU heterogeneous architecture parallel computing platform is developed to simulate incompressible flows on billion-level grid points. To solve the Poisson equation, the conjugate gradient method is used as a basic solver, and a Chebyshev method in combination with a Jacobi sub-preconditioner is used as a preconditioner. The developed CFD solver shows good performance on parallel efficiency, which exceeds 90% in the weak-scalability test when the number of grid points allocated to each GPU card is greater than 2083. In the acceleration test, it is found that running a simulation with 10403 grid points on 125 GPU cards accelerates by 203.6x over the same number of CPU cores. The developed solver is then tested in the context of a two-dimensional lid-driven cavity flow and three-dimensional Taylor-Green vortex flow. The results are consistent with previous results in the literature.
Found 
Found 

Top-30

Journals

1
Energy Storage Materials
Energy Storage Materials, 1, 33.33%
Energy Storage Materials
1 publication, 33.33%
Engineering Geology
Engineering Geology, 1, 33.33%
Engineering Geology
1 publication, 33.33%
1

Publishers

1
2
Elsevier
Elsevier, 2, 66.67%
Elsevier
2 publications, 66.67%
Institute of Electrical and Electronics Engineers (IEEE)
Institute of Electrical and Electronics Engineers (IEEE), 1, 33.33%
Institute of Electrical and Electronics Engineers (IEEE)
1 publication, 33.33%
1
2
  • We do not take into account publications without a DOI.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
3
Share
Cite this
GOST |
Cite this
GOST Copy
Li Q. et al. An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform // Theoretical and Applied Mechanics Letters. 2023. Vol. 13. No. 5. p. 100474.
GOST all authors (up to 50) Copy
Li Q., Li R., Yang Z. An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform // Theoretical and Applied Mechanics Letters. 2023. Vol. 13. No. 5. p. 100474.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1016/j.taml.2023.100474
UR - https://doi.org/10.1016/j.taml.2023.100474
TI - An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform
T2 - Theoretical and Applied Mechanics Letters
AU - Li, Qianqian
AU - Li, Rong
AU - Yang, Zixuan
PY - 2023
DA - 2023/09/01
PB - Elsevier
SP - 100474
IS - 5
VL - 13
SN - 2095-0349
ER -
BibTex |
Cite this
BibTex (up to 50 authors) Copy
@article{2023_Li,
author = {Qianqian Li and Rong Li and Zixuan Yang},
title = {An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform},
journal = {Theoretical and Applied Mechanics Letters},
year = {2023},
volume = {13},
publisher = {Elsevier},
month = {sep},
url = {https://doi.org/10.1016/j.taml.2023.100474},
number = {5},
pages = {100474},
doi = {10.1016/j.taml.2023.100474}
}
MLA
Cite this
MLA Copy
Li, Qianqian, et al. “An incompressible flow solver on a GPU/CPU heterogeneous architecture parallel computing platform.” Theoretical and Applied Mechanics Letters, vol. 13, no. 5, Sep. 2023, p. 100474. https://doi.org/10.1016/j.taml.2023.100474.