论文标题
SNE：基于稀疏事件的卷积的能源绩效数字加速器
SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions
论文作者
论文摘要
基于事件的传感器由于其高时间分辨率，低功耗和低带宽而引起了人们的注意。为了从该传感器产生的稀疏数据流中有效提取有意义的信息，我们提出了一个4.5TOP/S/W数字加速器，能够执行基于4位量化事件的卷积神经网络（ECNN）。与标准的卷积引擎相比，我们的加速器执行许多操作与输入数据流中包含的事件的数量成正比，最终达到了高能信息的处理比例。在IBM-DVS键盘数据集上，当输入活动为1.2％和4.9％时，我们分别报告80UJ/INF至261UJ/INF。据我们所知，我们的加速器消耗0.221pj/sop，这是数字神经形态发动机报道的最低能量/OP。
Event-based sensors are drawing increasing attention due to their high temporal resolution, low power consumption, and low bandwidth. To efficiently extract semantically meaningful information from sparse data streams produced by such sensors, we present a 4.5TOP/s/W digital accelerator capable of performing 4-bits-quantized event-based convolutional neural networks (eCNN). Compared to standard convolutional engines, our accelerator performs a number of operations proportional to the number of events contained into the input data stream, ultimately achieving a high energy-to-information processing proportionality. On the IBM-DVS-Gesture dataset, we report 80uJ/inf to 261uJ/inf, respectively, when the input activity is 1.2% and 4.9%. Our accelerator consumes 0.221pJ/SOP, to the best of our knowledge it is the lowest energy/OP reported on a digital neuromorphic engine.
