Abstract: High power amplifier (HPA) is one of the main sources of nonlinear distortion in wireless communication systems. Digital baseband predistortion technology can effectively reduce the nonlinear distortion and improve the system transmission performance. In this paper, a particle swarm optimization(PSO) algorithm was used directly to estimate the parameters of Hammerstein predsitorter model and to solve the local maximum problem of gradient algorithms. The predistortion algorithm was optimized into a parallel computing structure which could lead to the maximum acceleration rate of the algorithm greater than 3. Simulation results show that the proposed algorithm can effectively suppress the spectrum regrowth outside band and reduce ACPR about 25 dB.