Fast post-layout leakage ECO using graph convolutional network

Abstract

At the very late design stage, engineering change order (ECO) leakage optimization is often performed to swap some cells for the ones with lower leakage, e.g. the cells with higher threshold voltage (V th ) or with longer gate length. It is very effective but time consuming due to iterative nature of swap and timing check with correction. We introduce a graph convolutional network (GCN) for quick ECO leakage optimization. GCN receives a number of input parameters that model the current timing information of a netlist as well as the connectivity of the cells in a form of a selective connectivity matrix. Trained by given leakage optimization results, GCN performs initial V th assignment at once. To correct timing violation which may be introduced by mis-prediction of GCN as well as to remove any minimum implant width (MIW) violations, we propose a heuristic V th reassignment. The combined GCN and heuristic achieve 37% reduction of leakage, which can be compared to 42% reduction from commercial ECO, but with 77% runtime reduction.