Optimizing data-flow in Binary Neural Networks

L. Vorabbi,D. Maltoni,S. Santi

CoRR(2023)

引用 0|浏览14
暂无评分
摘要
Binary Neural Networks (BNNs) can significantly accelerate the inference time of a neural network by replacing its expensive floating-point arithmetic with bitwise operations. Most existing solutions, however, do not fully optimize data flow through the BNN layers, and intermediate conversions from 1 to 16/32 bits often further hinder efficiency. We propose a novel training scheme that can increase data flow and parallelism in the BNN pipeline; specifically, we introduce a clipping block that decreases the data-width from 32 bits to 8. Furthermore, we reduce the internal accumulator size of a binary layer, usually kept using 32-bit to prevent data overflow without losing accuracy. Additionally, we provide an optimization of the Batch Normalization layer that both reduces latency and simplifies deployment. Finally, we present an optimized implementation of the Binary Direct Convolution for ARM instruction sets. Our experiments show a consistent improvement of the inference speed (up to 1.91 and 2.73x compared to two state-of-the-art BNNs frameworks) with no drop in accuracy for at least one full-precision model.
更多
查看译文
关键词
Binary,Networks,Quantization,1-bit
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要