面向存内计算的近似ADC
Approximate ADCs for In-Memory Computing
AI总结:
针对存内计算中ADC功耗与面积占比过高、校准开销大的问题,提出将ADC及存储单元的非理想特性纳入深度学习模型训练的外围感知IMC核心设计,适用于两类MVM运算,可简化数模混合IMC单元设计。
摘要:
用于深度学习(DL)加速器的存内计算(IMC)架构利用了可直接在存储阵列中实现的高能效、高并行度矩阵向量乘法(MVM)运算。这类IMC设计已基于CMOS以及RRAM等新兴非易失性存储器(NVM)技术展开研究。IMC架构通常包含大量由存储阵列构成的核心,用于存储DL模型的训练后权重,同时还采用DAC、ADC等外围单元来施加输入并读取输出值。近期报道的设计显示,读取MVM结果所需的ADC消耗了总计算功耗的85%以上,且占据了主要面积,从而抵消了IMC方案的优势。由于需要专用校准单元,缓解ADC的非线性、偏差等缺陷会带来显著的设计开销。在本工作中,我们提出了具备外围感知能力的IMC核心设计以降低这类开销,其思路是将ADC的非理想特性与存储单元的非理想特性一同纳入DL模型的训练过程。该方法对近年出现的电流模式和电荷模式MVM运算均适用,可大幅简化数模混合IMC单元的设计。
英文摘要:
In memory computing (IMC) architectures for deep learning (DL) accelerators leverage energy-efficient and highly parallel matrix vector multiplication (MVM) operations, implemented directly in memory arrays. Such IMC designs have been explored based on CMOS as well as emerging non-volatile memory (NVM) technologies like RRAM. IMC architectures generally involve a large number of cores consisting of memory arrays, storing the trained weights of the DL model. Peripheral units like DACs and ADCs are also used for applying inputs and reading out the output values. Recently reported designs reveal that the ADCs required for reading out the MVM results, consume more than 85% of the total compute power and also dominate the area, thereby eschewing the benefits of the IMC scheme. Mitigation of imperfections in the ADCs, namely, non-linearity and variations, incur significant design overheads, due to dedicated calibration units. In this work we present peripheral aware design of IMC cores, to mitigate such overheads. It involves incorporating the non-idealities of ADCs in the training of the DL models, along with that of the memory units. The proposed approach applies equally well to both current mode as well as charge mode MVM operations demonstrated in recent years., and can significantly simplify the design of mixed-signal IMC units.
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。