用遗传算法直接演化电路网表，自动设计标准单元和运算放大器。
SPICEMixer - Netlist-Level Circuit Evolution
- 直接在网表行级操作，支持任意元件和通用遗传算子。
- 设计标准单元和运放均达标，仿真次数远少于现有方法。
- 适合集成电路自动化设计人员，尤其关注低资源优化者。
我们提出 SPICEMixer，一种通过直接演化 SPICE 网表来合成电路的遗传算法。该方法在单个网表行上操作，兼容任意元件与子电路，并支持通用遗传算子：交叉、变异和剪枝，全部在网表层级直接执行。为支持这些操作，我们通过统一命名（输入、输出、电源、内部节点）和固定组件与节点排序，对网表进行规范化，使相似电路结构在相同行位置出现，从而提升交叉、变异和剪枝的有效性。我们通过合成标准单元（如 NAND2、锁存器）和设计满足指定指标的运放，验证了 SPICEMixer 的有效性。在各项任务中，其性能达到或优于近期合成方法，且所需仿真次数显著减少。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。