Add to ORKGAbstract—As local random variations on Integrated Circuits are increasingly impacting circuit behavior, there is an increasing need to analyze the impact of these variations efficiently. A widely used tool to analyze circuit behavior is the SPICE-level simulator. To analyze the impact of random variations, these simulators are used inside a CPU-intensive Monte-Carlo loop in current industry practice. In this paper we show that it is possible to build a SPICE-level simulator with built-in statistical capabilities, to improve dramatically on the run time efficiency. I