This paper deals with multiprocessor systems required to provide both high performance and good figures of dependability attributes. Fault tolerance is pursued through a proper combination and integration of a diagnostic mechanism, called - count, with simple instances of redundancy-based error processing structures. The resulting fault tolerance strategies are then evaluated through a stochastic simulation approach, as dictated by the high interdependence of the selected mechanisms. The analysis is mainly carried out in terms of performability, which shows to be an appropriate measure to evaluate whether a certain design is "better" than another under dependability and performance points of view.