Method of construction of parallel systems for fuzzy logical inference based on GPU accelerators

S.V. Yershov, R.N. Ponomarenko

Abstract


We examine a new method for constructing parallel hierarchical systems of fuzzy logic inference using multi-tier parallel form of algorithms based on Nvidia GPU accelerators and CUDA technology. The efficiency of application of hierarchical systems of fuzzy inference for development of diagnostic intelligent system is substantiated. We characterize the organization of efficient computations on graphic accelerators with the aim of achieving maximum degree of parallelism in fuzzy hierarchical systems. In particular, the above organization relies on parallelization of rules inside each block of fuzzy rules. An intelligent software system for assessing the quality of startups based on parallel inference architecture that contains Takagi – Sugeno blocks of fuzzy rules is developed. The experiment is conducted to demonstrate acceleration estimates for developed intellectual system for assessing the quality of startups as well as for more complex systems with randomly generated dependencies between blocks of rules. We compare characteristics of the obtained acceleration estimates with corresponding estimates for hierarchical fuzzy systems based on the distributed computing technology and MPI message exchange. The advantages of developed method for construction of parallel fuzzy inference based on GPU are substantiated.

 Problems in programming 2017; 4: 003-015


Keywords


intelligent system; multi-tier parallel form of computing; GPU ace­lerators; fuzzy logic; Takagi – Sugeno system; CUDA

Full Text:

PDF (Ukrainian)

References


Parasyk I.N, Yershov S.V. (2012) Multilevel models base on fuzzy logic of the highest type for high-performance environment // Problems in programming. – N 2-3. P. 260–269.

Shtovba S.D. (2007) Fuzzy systems design by MATLAB mean // M.: Goryachaya liniya – Telecom – 288 p.

Torra V. (2002) A review of the construction of hierarchical fuzzy systems // Int. J. Intell. Syst. – Vol.17, N 5. – P. 531–543.

Yager R.R. (1993) On a hierarchical structure for fuzzy modeling and control // IEEE Trans. Syst. Man Cybern. – Vol. 23, N 4. – P. 1189–1197.

Yager R.R. (1998) On the construction of hierarchical fuzzy systems models // IEEE Trans. Syst. Man Cybern. – Vol. 28, N 1. – P. 55–66.

Cordon O., Herrera F., Zwir I. (2002) Linguistic modeling by hierarchical systems of linguistic rules // IEEE Trans. Fuzzy Syst. – N 10. – P. 2–20.

Raju G.V.S., Zhou J., Kisner R.A. (1991) Hierarchical fuzzy control // Int. J. Control. – Vol. 54, N 5. – P. 1201–1216.

Yershov S.V., Ponomarenko R.M. (2016) Parallel models for Takagi-Sugeno’s fuzzy multilevel systems // Problems in programming. – N 1. – P. 141–149.

Yershov S.V., Ponomarenko R.M. (2016) Tier parallel computing model for logical inference on fuzzy multilevel systems // Mathematic for computers. – N 1. – P. 28–36.

Voevodin V.V. (2002) Parallel inference // SPb: BHV-Peterburg. – 608 p.

Nvidia CUDA. – http://www.nvidia.com.ua/object/cuda-parallel-computing-ru.html

Doroshenko A.U., Beketov O.G. (2017) The cycle paralellization method of the mesh tasks for graphic accelerator // Problems in programming. – N 1. – P. 59–66.

Kiseleva E.M., Prytomanova O.M., Zhuravel S.V. (2016) Evaluation of the start-ups investment attractiveness base on the neuro-fuzzy technologies // Problems in management and informatics. – N 5. – P. 123–143.


Refbacks

  • There are currently no refbacks.