Hardware/Software Codesign for Training/Testing Multiple Neural Networks on Multiple FPGAs

Most neural network designs for FPGAs are inflexible. In this paper, we propose a flexible VHDL structure that would allow any neural network to be implemented on multiple FPGAs. Moreover, the VHDL structure allows for testing as well as training multiple neural networks. The VHDL design consists of...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-03
Main Author: Brosnan Yuen
Format: Article
Language:English
Subjects:
Activation
Co-design
Field programmable gate arrays
Hardware description languages
Microprocessors
Neural networks
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most neural network designs for FPGAs are inflexible. In this paper, we propose a flexible VHDL structure that would allow any neural network to be implemented on multiple FPGAs. Moreover, the VHDL structure allows for testing as well as training multiple neural networks. The VHDL design consists of multiple processor groups. There are two types of processor groups: Mini Vector Machine Processor Group and Activation Processor Group. Each processor group consists of individual Mini Vector Machines and Activation Processor. The Mini Vector Machines apply vector operations to the data, while the Activation Processors apply activation functions to the data. A ring buffer was implemented to connect the various processor groups.
ISSN:2331-8422