HIERARCHICAL YIELD ESTIMATION OF LARGE ANALOG INTEGRATED-CIRCUITS

A hierarchical Monte Carlo methodology for parametric yield estimation of large analog integrated circuits is presented. The methodology exploits the natural functional hierarchy of a circuit and employs a combination of behavioral and regression modeling to replace device-level circuit simulation where possible. Two related techniques for hierarchical yield estimation are demonstrated on a reasonably large BiCMOS circuit combining discrete-time and continuous-time operation. The hierarchical yield estimates agree well with the benchmark of device-level circuit simulation of the complete circuit and are less computationally expensive.