Reconfigurable Architectures: A New Vision for Optimization Problems

GSAT is a greedy local search procedure. It searches for satisfiable instantiations of formulas under conjunctive normal form. Intrinsically incomplete, this algorithm has shown its ability to deal with formulas of large size that are not yet accessible to exhaustive methods. Many problems such as planning, scheduling, vision can efficiently be solved by using the GSAT algorithm. In this study, we give an implementation of GSAT on Field Programmable Gate Arrays (FPGAs) in order to speed-up the resolution of SAT problems. By this implementation, our aim is to solve large SAT problems and to enable real-time resolution for current size problems. The FPGA technology [12] allows users to adapt a generic logic chip to different tasks. In the framework of SAT problems we show how to quickly adapt our chips to efficiently solve satisfiability problems.