In the multiprocessor system, scheduling is a major issue in their operation, which is also an important problem in other area such as manufacturing, process control, economics, operation research and, etc. An efficient scheduling that minimizes the entire run time and also average of response time is vital for achieving a high performance. Solving this problem is very hard and many attempts have been made to solve the prolem, using classical algorithms and intelligent methods. In this paper, an intelligent method has been proposed based on genetic algorithm that has better performance than classical algorithms. The optimal scheduling was presented by the best chromosome in last generation.