SpiceMixer -- Netlist-Level Circuit Evolution

2025-06-02

AI Summary

Traditional analog circuit synthesis methods suffer from strong dependencies on device types and topologies, high modeling costs, and poor generalizability. To address these limitations, this paper proposes SpiceMixer—a genetic algorithm framework that performs direct, line-level evolution on SPICE netlists. Its key contributions are: (1) the first netlist-line-level evolutionary paradigm, eliminating the need for explicit device or subcircuit modeling; (2) a standardized and normalized netlist representation, significantly enhancing the effectiveness and compatibility of genetic operators—including crossover, mutation, and pruning; and (3) simulation-driven fitness evaluation, enabling model-free synthesis across arbitrary device types. Experimental results demonstrate state-of-the-art performance on standard logic cells (inverters, NAND gates, latches) and achieve 89% test accuracy on an end-to-end synthesized analog Iris classifier—outperforming all existing approaches.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Evolutionary Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

This paper introduces SpiceMixer, a genetic algorithm developed to synthesize novel analog circuits by evolving SPICE netlists. Unlike conventional methods, SpiceMixer operates directly on netlist lines, enabling compatibility with any component or subcircuit type and supporting general-purpose genetic operations. By using a normalized netlist format, the algorithm enhances the effectiveness of its genetic operators: crossover, mutation, and pruning. We show that SpiceMixer achieves superior performance in synthesizing standard cells (inverter, two-input NAND, and latch) and in designing an analog classifier circuit for the Iris dataset, reaching an accuracy of 89% on the test set. Across all evaluated tasks, SpiceMixer consistently outperforms existing synthesis methods.

Problem

• Evolves SPICE netlists to synthesize novel analog circuits
• Enhances genetic operations via normalized netlist format
• Outperforms existing methods in analog circuit synthesis

Innovation

• Evolves SPICE netlists using genetic algorithm
• Operates directly on normalized netlist lines
• Enhances genetic operations like crossover and mutation