Abstract
An evolutionary model of modular associative memory for machines with dataflow architecture is suggested. A problem of determination of optimal allocation of a dataflow in a computational system with modular associative memory is formulated. The model suggested is based on graph representation of the dataflow. The allocation of the dataflow among modules is realized by means of a hash function. A method for searching for optimal hashing with the use of a genetic algorithm is suggested. The convergence of the genetic algorithm is studied. Estimates of optimal allocation among modules of associative memory for various computational problems are obtained.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.REFERENCES
Burtsev, V.S., A New System of Organization of Execution of Highly Parallel Computational Processes and Examples of Possible Architecture Solutions for Construction of Supercomputers, in Parallelizm vychislitel'nykh protsesov i razvitie arkhitektury super-EVM (Parallelism of Computational Processes and Development of Architectures for Supercomputers), Moscow, 1997.
Popadopolous, G. and Traub, K., Multithreading: A Revisionist View of Dataflow Architecture, Sigarch Comput. Arch. News, 1991, vol. 19, no. 3.
Burtsev, V.S. and Fedorov, V.B., Use of Optical Methods for Processing Information in the Supercomputer Architecture, in Parallelizm vychislitel'nykh protsesov i razvitie arkhitektury super-EVM (Parallelism of Computational Processes and Development of Architectures for Supercomputers), Moscow, 1997.
Burtsev, V.S. and Fedorov, V.B., Associative Memory Based on Optical Processing of Information for New-Generation Supercomputers, in Vychislitel'nye mashiny s netraditsionnoi arkhitekturoi. Super-VM (Computational Machines with Nontraditional Architecture: Supercomputers), vol. 2, Moscow, 1994.
Goldberg, D.E., Genetic Algorithms in Search, Optimization and Machine Learning, Reading, MA: Addison-Wesley, 1989.
De Jong, K., Evolutionary Computation: Recent Development and Open Issues, Proc. of EvCA'96.
Nikitin, A.V., Using GA for Parallelization of Programs, Proc. of EvCA'96.
Thang Nguyen Bui and Byung Ro Moon, Genetic Algorithm and Graph Partitioning, IEEE Trans. Comput., 1996, vol. 45, no. 7.
Nikitin, A.V. and Popov, A.M., Optimization of Modular Associative Memory, Chislennye metody i vychislitel'nyi eksperiment (Numerical Methods and Computational Experiment), Samarskii, A.A. and Dmitriev, V.I., Eds., Moscow: Dialog-MGU, 1998.
Ershov, N.M., An Algorithm for Parallelizing Computations Based on the Monte-Carlo Method, in Matematicheskie modeli estestvoznaniya (Mathematical Models in Natural Science), Moscow: Mosk. Gos. Univ., 1995.
Olenin, A.S., Representative Computations in Study of Computer Architectures, in Vychislitel'nye mashiny s netraditsionnoi arkhitekturoi. Super-VM (Computational Machines with Nontraditional Architecture: Supercomputers), vol. 6, Moscow, 1997.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Nikitin, A.V., Nikitina, L.I. Evolutionary Model of Optimization of Modular Associative Memory for Dataflow Machines Based on Genetic Algorithm. Programming and Computer Software 28, 324–332 (2002). https://doi.org/10.1023/A:1021097926343
Issue Date:
DOI: https://doi.org/10.1023/A:1021097926343