This paper presents the development of a multiinput multioutput generalized predictive control (GPC) law and its application to reconfigurable control design in the event of actuator saturation. The stability of the GPC control law without reconfiguration is first established using an end-point state weighting. Based on the constrained nonlinear optimization, an end-point state weighting matrix synthesis method is derived. A novel reconfiguration strategy is developed for systems that have actuator redundancy and are faced with actuator saturation type failure. An elegant reconfigurable control design is presented with stability proof. A numerical simulation using a short-period approximation model of a civil transport aircraft is presented to demonstrate the reconfigurable control architecture.