Data Streaming and Traffic Gathering in Mesh-based NoC for Deep Neural Network Acceleration

no code implementations • 1 Aug 2021 • Binayak Tiwari, Mei Yang, Xiaohang Wang, Yingtao Jiang

In this paper, we propose a modified mesh architecture with a one-way/two-way streaming bus to speedup one-to-many (multicast) traffic, and the use of gather packets to support many-to-one (gather) traffic.

Improving the Performance of a NoC-based CNN Accelerator with Gather Support

no code implementations • 1 Aug 2021 • Binayak Tiwari, Mei Yang, Xiaohang Wang, Yingtao Jiang, Venkatesan Muthukumar

For many-to-one traffic, repetitive unicast is employed which is not an efficient way.