A Power Efficient Neural Network Implementation on Heterogeneous FPGA and GPU Devices
Authors:
- 1 July 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 193-199
Abstract
Deep neural networks (DNNs) have seen tremendous industrial successes in various applications, including image recognition, machine translation, audio processing, etc. However, they require massive amounts of computations and take a lot of time to process. This quickly becomes a problem in mobile and handheld devices where real-time multimedia applications such as face detection, disaster management, and CCTV require lightweight, fast, and effective computing solutions. The objective of this project is to utilize specialized devices such as Field Programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs) in a heterogeneous computing environment to accelerate the deep learning computations with the constraints of power efficiency. We investigate an efficient DNN implementation and make use of FPGA for fully-connected layer and GPU for floating-point operations. This requires the deep neural network architecture to be implemented in a model parallelism system where the DNN model is broken down and processed in a distributed fashion. The proposed heterogeneous framework idea is implemented using an Nvidia TX2 GPU and a Xilinx Artix-7 FPGA. Experimental results indicate that the proposed framework can achieve faster computation and much lower power consumption.Keywords
This publication has 15 references indexed in Scilit:
- Integrated Model, Batch, and Domain Parallelism in Training Neural Networks2018
- Multimodal deep representation learning for video classificationWorld Wide Web, 2018
- Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification2018
- Accelerating Binarized Neural Networks: Comparison of FPGA, CPU, GPU, and ASIC2016
- Deep Residual Learning for Image Recognition2016
- A high performance FPGA-GPU-CPU platform for a real-time locating system2015
- An energy efficient hybrid FPGA-GPU based embedded platform to accelerate face recognition application2015
- A heterogeneous platform with GPU and FPGA for power efficient high performance computing2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012