Abstract: A method of finding the optimal placement of circuit elements is disclosed in which the optimal position of each circuit element is determined from the results of arithmetic operations performed by a processor network where a plurality of processors are interconnected so as to form a neural network, and each processor takes in its own output and the outputs of all other processors to solve a problem.

Abstract: Element placement optimizing method and apparatus for determining an optimum placement of constituent elements for an LSI or the like. A parallel processing type computer system including a plurality of CPUs is used. An initial element placement is established and a number of paired element candidates for position exchange are selected from the initial placement, the number being equal to that of CPUS. A cost improvement value resulting from the exchange is determined for each of the paired candidates by the associated CPU. The exchange of the elements is performed for the paired element candidates for which the cost improvement value is maximum of those determined by the CPUs. By repeating the exchange, an optimum element placement is determined.