A method, apparatus and system for multiplying a matrix by a vector, for example, video interpolation (other applications are contemplated). The matrix may be a representation of a large and sparse system of linear equations. The large and sparse system of linear equations may be used to estimate motion between frames of a video file for converting frame rates. The vector may be a first estimation of a solution to the system of linear equations. The matrix may be multiplied by elements of the vector in an order different from the order in which the elements are arranged in the vector. Elements in the vector may be multiplied in parallel. A second vector estimation of the solution to a system of linear equations may be a product of the multiplying. The solution to the system of linear equations may be set, for example, when the first and second vector estimations differ by less than a predetermined amount. Other embodiments are described and claimed.