A Decomposition method for solving quadratic programming (QP) with boxconstraints is presented in this paper. It is similar to the iterativemethod for solving linear system of equations. The main ideas of thealgorithm are to split the Hessian matrix Q of the QP problem into thesum of two matrices N and H such that Q=N+H and (N-H) is symmetric positive definite matrix ((N, H) is called a regular splitting of Q)[5]. A new quadratic programming problem with Hessianmatrix N to replace the original Q is easier to solve than theoriginal problem in each iteration. The convergence of thealgorithm is proved under certain assumptions, and the sequencegenerated by the algorithm converges to optimal solution and has alinear rate of R-convergence if the matrix Q is positive definite, ora stationary point for the general indefinite matrix Q, and thenumerical results are also given.