GM Plan: a gate matrix layout algorithm based on artificial intelligence planning techniques

In this paper, the gate matrix layout is formulated as a planning problem where a "plan" (the solution steps) is generated to achieve a "goal" (the gate matrix layout) that consists of subgoals interacting each other. Each subgoal corresponds to the placement of a gate to a slot. or to the routing of a net connecting gates. The interaction among subgoals is managed with two AI planning techniques: the hierarchical planning and the mcta-planning. A new distance measure is defined to arrange he. subgoals into pnoritized classes in the hierarchical planning. Two meta-planning policics-gracefd r e m and least impact-am used to decide which sub@ IS to be achieved within the same priority class and how it can be achieved. In doing so. GM-Plan successfully combines the gate placement and net routing of the gate matrix layout into one process and has the potential to dcliver better results.