LPSAT: a unified approach to RTL satisfiability

LPSAT is an LP-based comprehensive infrastructure designed to solve the satisfiability (SAT) problem for complex RTL designs containing both word-level arithmetic operators and bit-level Boolean logic. The presented technique uses a mixed integer linear program to model the constraints corresponding to both domains of the design. Our technique renders the constraint propagation between the two domains implicit to the MILP solver thus enhancing the overall efficiency of the SAT framework. The experimental results are quite promising when compared with generic CNF-based and BDD-based SAT algorithms.