局部归一化的模拟存内计算的能量界研究
Investigating Energy Bounds of Analog Compute-in-Memory with Local Normalization
AI总结:
针对模拟存内计算中动态范围导致ADC能耗高的问题,提出增益范围MAC(GR-MAC)实现局部归一化,在35 dB SQNR下将输入动态范围提升4位而不增加能耗,并降低ADC分辨率需求1.5位。
摘要:
现代边缘AI工作负载要求最大能量效率,推动了模拟存内计算(CIM)架构的追求。同时,大型语言模型(LLM)的普及驱动了优先考虑动态范围的低位浮点格式的采用。然而,传统的直接累加CIM通过将浮点数归一化到共享的加宽定点尺度来适应浮点数。因此,硬件分辨率由输入的动态范围而非精度决定,能耗由ADC主导。我们通过引入局部归一化,对每个输入、权重和乘累加(MAC)输出采用增益范围MAC(GR-MAC)来解决这一限制。归一化开销由低功耗数字逻辑处理,使计算昂贵的MAC操作保持在节能的低精度模拟域。能量建模表明,在MAC中添加增益范围级可在35 dB SQNR标准下实现输入动态范围增加4位而不增加能耗。此外,ADC分辨率要求变得与输入分布假设无关,允许构建一个上界,与传统下界相比减少1.5位。这些结果为解锁模拟CIM对现代AI工作负载有利的能量缩放趋势铺平了道路。
英文摘要:
Modern edge AI workloads demand maximum energy efficiency, motivating the pursuit of analog Compute-in-Memory (CIM) architectures. Simultaneously, the popularity of Large-Language-Models (LLMs) drives the adoption of low-bit floating-point formats which prioritize dynamic range. However, the conventional direct-accumulation CIM accommodates floating-points by normalizing them to a shared widened fixed-point scale. Consequently, hardware resolution is dictated by the input's dynamic range rather than its precision, and energy consumption is dominated by the ADC. We address this limitation by introducing local normalization for each input, weight, and multiply-accumulate (MAC) output via a Gain-Ranging MAC (GR-MAC). Normalization overhead is handled by low-power digital logic, enabling the computationally expensive MAC operation to remain in the energy-efficient low-precision analog regime. Energy modelling shows that the addition of a gain-ranging Stage to the MAC enables a 4-bit increase in input dynamic range without increased energy consumption at a 35 dB SQNR standard. Additionally, the ADC resolution requirement becomes invariant to input distribution assumptions, allowing construction of an upper bound with a 1.5-bit reduction compared to the conventional lower bound. These results establish a pathway towards unlocking favourable energy scaling trends of analog CIM for modern AI workloads.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。