SPICEMixer - Netlist-Level Circuit Evolution

2025/06/02 by Stefan Uhlich, Uhlich, Stefan, Andrea Bonetti +12
Engineering · #Advancements in Semiconductor Devices and Circuit Design #B.7.0 #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Semiconductor materials and devices #VLSI and FPGA Design Techniques

paper · pdf · doi:10.48550/arxiv.2506.01497

openalex publication_date 2025/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present SPICEMixer, a genetic algorithm that synthesizes circuits by directly evolving SPICE netlists. SPICEMixer operates on individual netlist lines, making it compatible with arbitrary components and subcircuits and enabling general-purpose genetic operators: crossover, mutation, and pruning, all applied directly at the netlist level. To support these operators, we normalize each netlist by enforcing consistent net naming (inputs, outputs, supplies, and internal nets) and by sorting components and nets into a fixed order, so that similar circuit structures appear at similar line positions. This normalized netlist format improves the effectiveness of crossover, mutation, and pruning. We demonstrate SPICEMixer by synthesizing standard cells (e.g., NAND2 and latch) and by designing OpAmps that meet specified targets. Across tasks, SPICEMixer matches or exceeds recent synthesis methods while requiring substantially fewer simulations.

Citations

• AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies
• Locality-aware Surrogates for Gradient-based Black-box Optimization
• AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Models
• Schemato -- An LLM for Netlist-to-Schematic Conversion
• GraCo -- A Graph Composer for Integrated Circuits
• AnalogCoder: Analog Circuit Design via Training-Free Code Generation
• Circuit-centric Genetic Algorithm (CGA) for Analog and Radio-Frequency Circuit Optimization
• CktGNN: Circuit Graph Neural Network for Electronic Design Automation
• DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using\n Deep Neural Networks
• AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• The CMA Evolution Strategy: A Tutorial

Related

• Masala-CHAI: A Large-Scale SPICE Netlist Dataset for Analog Circuits by Harnessing AI
• Multitask Evolution with Cartesian Genetic Programming
• GenEDA: Towards Generative Netlist Functional Reasoning via Cross-Modal Circuit Encoder-Decoder Alignment
• SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidance
• Python Framework for Modular and Parametric SPICE Netlists Generation