BinarEye: An Always-On Energy-Accuracy-Scalable Binary CNN Processor With All Memory On Chip in 28nm CMOS
This work addresses energy efficiency for always-on AI applications like face detection and owner recognition, representing a significant advance in hardware design rather than an incremental improvement.
The paper tackles the problem of energy-efficient always-on binary convolutional neural network processing by introducing BinarEye, a chip that achieves a peak efficiency of 230 1b-TOPS/W and reduces full system energy consumption to as low as 0.92uJ/f for face detection at 94% accuracy, which is 3-70x more efficient than state-of-the-art methods.
This paper introduces BinarEye: a digital processor for always-on Binary Convolutional Neural Networks. The chip maximizes data reuse through a Neuron Array exploiting local weight Flip-Flops. It stores full network models and feature maps and hence requires no off-chip bandwidth, which leads to a 230 1b-TOPS/W peak efficiency. Its 3 levels of flexibility - (a) weight reconfiguration, (b) a programmable network depth and (c) a programmable network width - allow trading energy for accuracy depending on the task's requirements. BinarEye's full system input-to-label energy consumption ranges from 14.4uJ/f for 86% CIFAR-10 and 98% owner recognition down to 0.92uJ/f for 94% face detection at up to 1700 frames per second. This is 3-12-70x more efficient than the state-of-the-art at on-par accuracy.