发表机构
Brown University; Google; University of Michigan（布朗大学; 谷歌; 密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CircuitsDNA是一种进化框架，可自动进化出单电路内多精度模式的算术电路，其8位乘法器在面积功耗比、收敛速度等方面优于传统方法，精度损失可控。
AI 中文摘要
新兴边缘AI workload日益需要可按需在计算精度与效率间权衡的算术单元。然而，现有近似算术电路通常是固定精度的，或依赖预定义结构实现运行时可配置性。本研究提出CircuitsDNA，一种进化框架，可自动进化出支持单电路内多种精度模式的精度可配置算术电路。它整合了三大核心特性：1）多阈值可验证斜接器，用于强制特定模式的精度要求；2）资源受限的可验证驱动搜索，在不牺牲正确性的前提下降低验证开销，实现对大型电路设计的高效探索；3）反馈驱动的自适应变异，用于优先考虑有效的结构修改并加速搜索收敛。实验结果显示，在28nm CMOS工艺下合成的8位乘法器变体，与精确8位乘法器相比，在INT8 DNN workload下面积-功耗乘积最多降低56%，在穷尽活动下最多降低93%。在 worst-case error（WCE）预算最多为1%的情况下，经过微调后，其相对于FP32的精度损失在CNN和DeiTs上均低于2%。CircuitsDNA消除了传统方法在8/12/16位乘法器上观察到的所有搜索停滞，且自适应变异相比非自适应对应物提供了最多1.33倍的收敛速度提升。
英文摘要
Emerging edge AI workloads increasingly require arithmetic units that can trade computational accuracy for efficiency on demand. However, existing approximate arithmetic circuits are typically fixed-accuracy or rely on predefined structures for runtime configurability. This work introduces CircuitsDNA, an evolutionary framework that automatically evolves accuracy-configurable arithmetic circuits supporting multiple accuracy modes within a single circuit. It integrates three key features: 1) multi-threshold verifiability miter to enforce mode-specific accuracy requirements, 2) resource-limited verifiability-driven search to reduce verification overhead without sacrificing correctness, enabling efficient exploration of large circuit design, and 3) feedback-driven adaptive mutation to prioritize effective structural modifications and accelerate search convergence. Experimental results show that the 8-bit multiplier variants synthesized in 28-nm CMOS reduce the area-power product by up to 56% on INT8 DNN workload and 93% under exhaustive activity, compared with an exact 8-bit multiplier. Across CNNs and DeiTs, the accuracy loss relative to FP32 remains below 2% after fine-tuning under worst-case error (WCE) budgets of at most 1%. CircuitsDNA eliminates all search stalls observed in conventional methods across 8/12/16-bit multipliers, while adaptive mutation provides up to 1.33 times faster convergence than its non-adaptive counterpart.
