Machine Learning Framework Using Complex Network Features to Predict Wire-length

Recently, the research of performance prediction with prior knowledge obtained by machine learning (ML) techniques has been widely studied. In this paper, we present the first work of machine learning framework using complex network features to predict wire-length in physical design. The experimental result on TAU 2017 Benchmark shows the effectiveness and efficiency of our method. The predictors based on four machine learning models provide a high accuracy and reasonable speed compared with normal EDA (Electronic Design Automation) tool.