论文标题
模拟深度学习硬件的自适应块浮点
Adaptive Block Floating-Point for Analog Deep Learning Hardware
论文作者
论文摘要
模拟混合信号（AMS）设备应比其数字对应物更快，更节能的深神经网络（DNN）推断。但是，最近的研究表明，在AMS设备上的DNN具有固定点数，可能会因精确损失而导致准确的罚款。为了减轻这种惩罚，我们提出了一种新颖的AMS兼容自适应块浮点数（ABFP）编号表示。我们还引入放大（或增益）作为提高数字表示准确性的方法，而无需提高输出的位精度。我们评估了MLPERF数据中心推理基准中ABFP对DNNS的有效性 - 与Float32相比，准确度的准确性少于$ 1 \％$。我们还提出了一种针对AMS设备（差异噪声燃料（DNF））的新型固定方法，该方法与传统的量化感知训练相比，将设备噪声采样以加快固定速度。
Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital counterparts. However, recent studies show that DNNs on AMS devices with fixed-point numbers can incur an accuracy penalty because of precision loss. To mitigate this penalty, we present a novel AMS-compatible adaptive block floating-point (ABFP) number representation. We also introduce amplification (or gain) as a method for increasing the accuracy of the number representation without increasing the bit precision of the output. We evaluate the effectiveness of ABFP on the DNNs in the MLPerf datacenter inference benchmark -- realizing less than $1\%$ loss in accuracy compared to FLOAT32. We also propose a novel method of finetuning for AMS devices, Differential Noise Finetuning (DNF), which samples device noise to speed up finetuning compared to conventional Quantization-Aware Training.
