HIGH PERFORMANCE COMPUTING ARCHITECTURE FOR FLUID DYNAMICS AND FLUID-STRUCTURE INTERACTION

Autores

  • Luiz Felipe Marchetti do Couto USP
  • Henrique Campelo Gomes USP
  • Paulo de Mattos Pimenta USP

DOI:

https://doi.org/10.26512/ripe.v2i35.21422

Palavras-chave:

Fluid-Structure Interaction. Finite Elements. High Performance Computing. GPU. CUDA.

Resumo

One of the biggest challenges of engineering is enablecomputational solutions that reduce processing time and provide more accurate numerical solutions. Proposals with several approaches that explore new ways of solving such problems or improve existing solutions emerge. Some of the areas dedicated to propose such improvements is the parallel and high performance computing. Techniques that improve the processing time, more efficient algorithms and faster computers open up new horizons allowing to perform tasks that were previously unfeasible or would take too long to complete. We can point out, among several areas of interest, Fluid Dynamics and Fluid-Structure Interaction. In this work it was developed a parallel computing architecture in order to solve numerical problems more efficiently, compared to sequential architecture (e.g. Fluid Dynamics and Fluid-Structure Interaction problems) and it is also possible to extend this architecture to solve different problems (e.g. Structural problems). The objective is to develop an efficient computational algorithm in scientific programming language C ++, based on previous work carried out in Computational Mechanics Laboratory (CML) at Polytechnic School at University of São Paulo, and later with the developed architecture, execute and investigate Fluid Dynamics and Fluid-Structure Interaction problems with the aid of CML computers. A sensitivity analysis is executed for different problems in order to assess the best combination of elements quantity and speedup, and then a perfomance comparison. Using only one GPU, we could get a 10 times speedup compared to a sequential software, using Finite Element with Immersed Boundary Method and a direct solver (PARDISO).

Downloads

Não há dados estatísticos.

Referências

Amdahl, G. M., 1967. Validity of the Single Processor Approach to Achieving Large-Scale

Computing Capabilities.

Cecka, C., Lew, A. J., Darve, E., 2011. Assembly of Finite Element Methods on graphics

processors. International Journal for Numerical Methods in Engineering, vol. 85, n. 5, pp.

”“669.

Couto, L. F. M., 2016. Arquitetura de computação paralela aplicada a problemas de dinâmica

dos fluidos e interação fluido-estrutura. Universidade de São Paulo.

Farber, R., 2011. CUDA application design and development. Elsevier.

Gamnitzer, P., 2010. Residual-based variational multiscale methods for turbulent flows and

fluid-structure interaction. Ph.D. Technischen Universitat Munchen.

Gomes, H. C., 2013. Método dos Elementos Finitos com Fronteiras Imersas aplicado a problemas

de dinâmica dos fluidos e interação fluido-estrutura. Ph. D.: Universidade de São Paulo.

Gomes, H. C., Pimenta, P. M., 2015. Embedded interface with discontinuous Lagrange multipliers

for fluid-structure interaction analysis. International Journal for Computational Methods

in Engineering Science and Mechanics, vol. 16, pp. 98”“111.

Lieu, T., Farhat, C., Lesoinne, M., 2006. Reduced-order fluid/structure modeling of a complete

aircraft configuration. Computer Methods in Applied Mechanics and Engineering, vol. 195, n.

-43, pp. 5730”“5742.

Schaffer, M., Turek, S., Durst, F., Krause, E., Rannacher, R., 1996. Benchmark computations

of laminar flow around a cylinder. Flow Simulation with High-Performance Computers II, vol.

, pp. 547”“566.

Sudhakar, Y., De Almeida, J. P. M., Wall, W. A., 2014. An accurate, robust, and easytoimplement

method for integration over arbitrary polyhedra: Application to embedded interface

methods. Journal of Computational Physics, vol. 273, pp. 393”“415.

Tezduyar, T. E., Sathe, S., Senga, M., Aureli, L., 2005. Finite element modeling of fluidstructure

interactions with spacetime and advanced mesh update techniques. Zilina, Slovakia.

Downloads

Publicado

2017-08-22

Como Citar

Couto, L. F. M. do, Gomes, H. C., & Pimenta, P. de M. (2017). HIGH PERFORMANCE COMPUTING ARCHITECTURE FOR FLUID DYNAMICS AND FLUID-STRUCTURE INTERACTION. Revista Interdisciplinar De Pesquisa Em Engenharia, 2(35), 113–134. https://doi.org/10.26512/ripe.v2i35.21422