Can I read Light-OPU: An FPGA-based Overlay Processor for Lightweight Convolutional Neural Networks on EtoBox?

Light-OPU: An FPGA-based Overlay Processor for Lightweight Convolutional Neural Networks by Yu, Yunxuan ;Zhao, Tiandong ;Wang, Kun ;He, Lei is a scholarly article available to read on EtoBox.

What is Light-OPU: An FPGA-based Overlay Processor for Lightweight Convolutional Neural Networks about?

Lightweight convolutional neural networks (LW-CNNs) such as MobileNet, ShuffleNet, SqueezeNet, etc., have emerged in the past few years for fast inference on embedded and mobile system. However, lightweight operations limit acceleration potential by GPU due to their memory bounded nature and their parallel mechanisms that are not friendly to SIMD. This calls for more specific accelerators. In this paper, we propose an FPGA-based overlay processor with a corresponding compilation flow for general LW-CNN accelerations, called Light-OPU. Software-hardware co-designed Light-OPU reformulates and decomposes lightweight operations for efficient acceleration. Moreover, our instruction architecture considers sharing of major computation engine between LW operations and conventional convolution operations. This improves the run-time resource efficiency and overall power efficiency. Finally, Light-OPU is software programmable, since loading of compiled codes and kernel weights completes switch of targeted network without FPGA reconfiguration. Our experiments on seven major LW-CNNs show that Light-OPU achieves 5.5× better latency and 3.0× higher power efficiency on average compared with edge G

Author

Yu, Yunxuan ;Zhao, Tiandong ;Wang, Kun ;He, Lei

Publisher

ACM

Published

2020

Language

EN