Reason-A Technical Journal (Formerly Reason-A Technical Magazine)

Open Access Open Access  Restricted Access Subscription Access

Optimization of Truss Structure Using Genetic Algorithm Performed on GPU


Affiliations
1 Dept. of Mechanical Engineering, IIT Guwahati, Guwahati, India
 

Modern Graphics Processing Units (GPU), offer a tremendous computing power, that is frequently an order of magnitude larger than even the most modern multi-core CPUs, making them an attractive platform for high performance computing due to their relative cheapness compared with conventional PC clusters. General purpose computing on GPUs (GPGPU) is becoming popular in High Performance Computing (HPC) because of its high peak performance. In this paper, a typical two-dimensional truss structure optimization problem is solved using Binary Genetic Algorithm (BGA) on both CPU and GPU. The kernel inside the GPU code computes the nodal displacements and elemental stresses by Finite Element Analysis (FEA) to evaluate the objective function and the constraints while making use of the Single Instruction Multiple Data (SIMD) structure of GPU to attain parallelization. The results are assessed for different values of parameters, such as complexity of the problem, number of elements, population size, maximum allowable generations and number of threads etc. to demonstrate how the value of speedup varies with these parameters and to provide a basic guideline for choosing the parameters for a different problem. The results clearly establish that calculations are performed considerably faster through the GPU than through the CPU in general.

Keywords

GPU, Genetic Algorithm, GPGPU, Topology Optimization.
User
Notifications
Font Size


  • Chen, G., Li, G., Pei, S. and Wu, B. High Performance Computing Via a GPU, Proceedings of the 1st International Conference on Information Science and Engineering, 2009.

  • Coello, C.A., Rudnick, M. and Christiansen, A.D., Using Genetic Algorithms for Optimal Design of Trusses, IEEE Event, Tulane University, New Orleans, 1994.

  • Buckles, B.P. and Petry, F.E., Genetic Algorithms. Technology Series. IEEE Computer Society Press, 1992.

  • Goldberg, D.E. and Samtani, M.P., Engineering Optimization Via Genetic Algorithm, Proceedings of Ninth Conference on Electronic Computation, New York, pp.471-482, 1986.

  • Deb, K., Optimal Design of a Welded Beam via Genetic Algorithms, Proceedings of AIAA Journal, Vol.29, pp.2013-2015, 1991.

  • Jenkins, W.M., Plane Frame Optimum Design Environment Based on Genetic Algorithm, Journal of Structural Engineering, Vol.118, No.11, pp.3103-3013, 1992.

  • Rajeev, S., Krishnamoorthy, C.S., Discrete Optimization of Structures using Genetic Algorithms, Journal of Structural Engineering, Vol.118, No.5, pp.1233-1250, 1992.

  • Papadrakakis, M., Lagaros, N.D. and Fragakis, Y., Parallel Computational Strategies for Structural Optimization, International Journal of Numerical Methods in Engng, 2003.

  • Cazacu, R. and Grama, L., Steel Truss Optimization Using Genetic Algorithms and FEA, Procedia Technology, Vol.12, pp.339346, 2014.

  • Ruiyi, S., Liangjin, G. and Zijie, F., Truss Topology Optimization Using Genetic Algorithm with Individual Identification, Proceedings of the World Congress on Engineering, Vol. 2, 2009.


Abstract Views: 420

PDF Views: 142




  • Optimization of Truss Structure Using Genetic Algorithm Performed on GPU

Abstract Views: 420  |  PDF Views: 142

Authors

Subhajit Sanfui
Dept. of Mechanical Engineering, IIT Guwahati, Guwahati, India
Ashish V. Gajbhiye
Dept. of Mechanical Engineering, IIT Guwahati, Guwahati, India

Abstract


Modern Graphics Processing Units (GPU), offer a tremendous computing power, that is frequently an order of magnitude larger than even the most modern multi-core CPUs, making them an attractive platform for high performance computing due to their relative cheapness compared with conventional PC clusters. General purpose computing on GPUs (GPGPU) is becoming popular in High Performance Computing (HPC) because of its high peak performance. In this paper, a typical two-dimensional truss structure optimization problem is solved using Binary Genetic Algorithm (BGA) on both CPU and GPU. The kernel inside the GPU code computes the nodal displacements and elemental stresses by Finite Element Analysis (FEA) to evaluate the objective function and the constraints while making use of the Single Instruction Multiple Data (SIMD) structure of GPU to attain parallelization. The results are assessed for different values of parameters, such as complexity of the problem, number of elements, population size, maximum allowable generations and number of threads etc. to demonstrate how the value of speedup varies with these parameters and to provide a basic guideline for choosing the parameters for a different problem. The results clearly establish that calculations are performed considerably faster through the GPU than through the CPU in general.

Keywords


GPU, Genetic Algorithm, GPGPU, Topology Optimization.

References





DOI: https://doi.org/10.21843/reas%2F2015%2F9-18%2F108326