仅充电一次2.0：采用可重构开关电容的端到端内存内模拟计算架构
You Only Charge Once 2.0 : A End-to-End Analog Computing-in-Memory Architecture with Reconfigurable Switched Capacitors
中文总结 AI 辅助
该研究提出Charge-CIM架构，以开关电容电荷重分配为统一基底，解决ACiM的ADC墙问题，在DNN基准上实现ADC能耗大降91.7%，能效提升2.7倍、吞吐量提升2.0倍。
中文摘要 AI 辅助
内存内模拟计算（ACiM）通过将权重存储在内存阵列中并在模拟域内执行点积来加速深度神经网络。然而，现代ACiM加速器常受限于“ADC墙”：模数转换器（ADC）消耗了大量的能量和面积，而位切片执行会反复调用这些转换器。现有设计通过低分辨率读出或时间复用降低该成本，但要么损失输出保真度，要么引入序列化开销。Charge-CIM通过采用开关电容电荷重分配作为统一的计算与转换基底来解决这一瓶颈：同一电容结构可执行输入转换、模拟乘累加（MAC）、加权移位加以及读出量化，既减少了独立转换器的开销，也减少了中间ADC的调用次数。差分读出路径在ADC量化过程中进一步组合配对的部分和，为阵列集成提供了高度紧凑且高能效的解决方案。借助数据流架构的支持，研究人员在从卷积神经网络（CNNs）到Transformer模型的一系列DNN基准上评估了Charge-CIM，实验结果显示，在评估设置下，Charge-CIM将ADC能量降低了91.7%，与最先进的电荷域CIM加速器相比，能量效率提升了2.7倍，吞吐量提升了2.0倍。
英文摘要
Analog Computing-in-Memory (ACiM) accelerates deep neural networks by keeping weights inside memory arrays and executing dot products in the analog domain. However, modern ACiM accelerators are often limited by the "ADC wall": analog-to-digital converters consume a large fraction of energy and area, while bit-sliced execution repeatedly invokes these converters. Existing designs reduce this cost with low-resolution readout or time multiplexing, but they either lose output fidelity or introduce serialization overhead. Charge-CIM addresses this bottleneck by using switched-capacitor charge redistribution as a unified computing and conversion substrate. The same capacitor fabric performs input conversion, analog MAC, weighted shift-and-add, and readout quantization, reducing both standalone converter overhead and intermediate ADC invocations. A differential readout path further combines paired partial sums during ADC quantization, providing a highly compact and energy-efficient solution for array integration. With dataflow architecture support, we evaluated Charge-CIM on a suite of DNN benchmarks, from CNNs to Transformer models, and experimental results show that Charge-CIM reduces ADC energy by 91.7% under our evaluation setup and improves energy efficiency by 2.7x and throughput by 2.0x compared to the state-of-the-art charge-domain CIM accelerator.
