Design of compact memristive in-memory computing systems using model counting

Crossbars of nanoscale memristors are being fabricated to serve as high-density non-volatile memory devices. The flow of current through memristor crossbars has been recently used to perform in-memory computations. However, existing approaches based on decision procedures only scale to the simplest circuits such as one-bit adders and other approaches employing decision diagrams produce large crossbar designs. In this paper, we present a new method for synthesizing compact combinational circuits using nanoscale crossbars. Our synthesis procedure exploits a symbolic representation of Boolean functions and employs model counting to guide a simulated annealing based search procedure. The proposed method creates crossbars that are up to about 6.3 times more compact than crossbars synthesized using decision diagrams. Our approach can scale to problems at least 4 times larger than the approach based on quantified decision procedures.