在聚集支持下提高NoC-based CNN加速器的性能
Improving the Performance of a NoC-based CNN Accelerator with Gather Support
摘要：
深度学习技术的日益广泛应用推动了对卷积神经网络（CNN）的高效并行计算架构的需求。设计众核CNN加速器时面临的一个重大挑战是处理处理元件之间的数据移动。除了一对一和一对多流量之外，CNN工作负载还引入了多对一流量。片上网络作为片上通信的事实标准，能够支持各种单播和组播业务。对于多对一业务，采用重复单播，这不是一种有效的方式。在本文中，我们提出了使用收集数据包的网格为基础的片上网络采用输出固定脉动阵列，支持多对一的流量。收集分组将从最终高效地通向目的地的中间结点收集数据。使用AlexNet和VGG-16的卷积层生成的流量跟踪来评估该方法，与重复单播方法相比，该方法在延迟和功率方面有所改善。
英文摘要：
The increasing application of deep learning technology drives the need for an efficient parallel computing architecture for Convolutional Neural Networks (CNNs). A significant challenge faced when designing a many-core CNN accelerator is to handle the data movement between the processing elements. The CNN workload introduces many-to-one traffic in addition to one-to-one and one-to-many traffic. As the de-facto standard for on-chip communication, Network-on-Chip (NoC) can support various unicast and multicast traffic. For many-to-one traffic, repetitive unicast is employed which is not an efficient way. In this paper, we propose to use the gather packet on mesh-based NoCs employing output stationary systolic array in support of many-to-one traffic. The gather packet will collect the data from the intermediate nodes eventually leading to the destination efficiently. This method is evaluated using the traffic traces generated from the convolution layer of AlexNet and VGG-16 with improvement in the latency and power than the repetitive unicast method.
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。
