A global asymptotic stability problem of cellular neural networks with delay is investigated. A new stability condition is presented based on the Lyapunov-Krasovskii method, which is dependent on the amount of delay. A result is given in the form of a linear matrix inequality, and the admitted upper
bound of the delay can be easily obtained. The time delay dependent
and independent results can be obtained, which include some previously published results. A numerical example is given to show the effectiveness of the main results.