Computer chip is always accompanied by the increase of heat dissipation and miniaturization, a system to predict the temperature of the semiconductor chip is presented by integrating the grey model and the computation fluid dynamics techniques. In the present methodology, one hundred sets of training data obtained from the CFD simulations results were sent to the grey model for the training. There are other eight generated input sets to be the test data and compared the results between CFD simulation and grey, it shows that the grey model is able to accurately estimate the corresponding temperature distribution as well as the maximum temperature values under different power distribution after well trained. Finally results show that the grey model only needs a few experimentation data and more accurate than CFD model.