Design of a processing element of a SIMD computer for geneticalgorithms

摘要

We have been investigating the efficiency of genetic algorithms(GA) for solving for a variety of real problems. During ourinvestigations we have concluded that the large amount of computationaltime required to find GA based solutions on conventional computers isrestrictive. We are therefore developing an innovative new computerarchitecture, suitable for the solution of large scale problems usingGAs. In this paper we introduce the SIMD-GA (Single Instruction streamMultiple Data stream Genetic Algorithm), and discuss its hardware designand implementation. By taking advantage of the recent advances is HDLs(Hardware Description Language) and FPGAs (Field Programmable GateArray) we have been able to quickly develop and prototype a PE(Processing Element) for a SIMD-GA. This approach allows us to build acost-effective parallel processing architecture to overcome the problemof the computational time required for traditional sequential GAimplementation