AI 中文总结
针对模拟存内计算中ADC读出对噪声敏感的问题，提出用随机参考1位感测和轻量计数替代多比特ADC，将电流转为概率以平均噪声，在ViT-Base上验证了抗噪性和抗相关性。
AI 中文摘要
模拟存内计算（CIM）能够实现高能效的模型加速，但其依赖于基于ADC的读出机制，该机制直接量化含噪的列电流，使得推理精度对模拟读出噪声、有效行缩放和ADC精度高度敏感。在本文中，我们提出了NOVA-CIM，一种用于模拟CIM的抗噪声与抗相关随机接口，通过用随机参考1位感测替代多位ADC读出，并通过轻量级计数重建结果。通过将列电流转换为比较概率，这种概率域读出在随机样本上平均零均值动态读出噪声，同时减少对高分辨率ADC的依赖。我们提供了一种统一的鲁棒性分析，表明动态读出噪声通过时间平均被抑制，并且空间输入比特流相关性会增加瞬时电流方差，而不是引入一阶MAC偏差。MAC级实验和在ViT-Base上的端到端评估验证了该分析：在读出噪声下，Top-1准确率保持在84.48%，接近84.51%的bfloat16（BF16）基线；在随机数生成器（SNG）重用下，MAC偏差保持接近零，而均方根误差（RMSE）和随机互相关（SCC）按预测增长。
英文摘要
Analog compute-in-memory (CIM) enables energy-efficient model acceleration, but its reliance on ADC-based readout, which directly quantizes noisy column currents, makes inference accuracy highly sensitive to analog read noise, active-row scaling, and ADC precision. In this paper, we present NOVA-CIM, a noise- and correlation-tolerant stochastic interface for analog CIM by replacing multi-bit ADC readout with random-reference 1-bit sensing and reconstructing results through lightweight counting. By converting column currents into comparison probabilities, this probability-domain readout averages zero-mean dynamic read noise over stochastic samples while reducing dependence on high-resolution ADCs. We provide a unified robustness analysis showing that dynamic read noise is suppressed through temporal averaging and that spatial input-bitstream correlation increases instantaneous current variance rather than introducing first-order MAC bias. MAC-level experiments and end-to-end evaluation on ViT-Base validate the analysis: under read noise, Top-1 accuracy remains 84.48% near the 84.51% bfloat16 (BF16) baseline; under stochastic number generator (SNG) reuse, MAC bias stays near zero while root-mean-square error (RMSE) and stochastic cross-correlation (SCC) grow as predicted.
CommentsWithdrawn because this version was submitted and announced without the agreement of all listed co-authors. The authors do not authorize this version for citation
