iVAMS: Intelligent metamodel-integrated Verilog-AMS for circuit-accurate system-level mixed-signal design exploration

The gap between abstraction levels in analog design is a major obstacle for advancing analog and mixed-signal design automation. Intelligent surrogate models for low-level analog building blocks are needed to bridge behavioral and transistor-level simulations. With this objective, artificial neural network (ANN) metamodels are incorporated in Verilog-AMS to capture the highly nonlinear response of the analog block. Parameterized ANN Verilog-AMS behavioral metamodels are constructed for efficient system-level design exploration. The application of these intelligent metamodels to multi-objective analog block optimization is demonstrated. To the best of the authors' knowledge this is the first paper to integrate artificial neural network models in Verilog-AMS. To demonstrate the application of iVAMS, a biologically-inspired “firefly optimization algorithm” is applied to an OP-AMP design. The optimization process is sped up by 5580× due to the use of iVAMS with negligible loss in accuracy.