MALOC: A Fully Pipelined FPGA Accelerator for Convolutional Neural Networks With All Layers Mapped on Chip

Recently, field-programmable gate arrays (FPGAs) have been widely used in the implementations of hardware accelerator for convolutional neural networks (CNNs). However, most of these existing accelerators are designed in the same idea as their ASIC counterparts, in which all operations from differen...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on computer-aided design of integrated circuits and systems Vol. 37; no. 11; pp. 2601 - 2612
Main Authors: Gong, Lei, Wang, Chao, Li, Xi, Chen, Huaping, Zhou, Xuehai
Format: Journal Article
Language:English
Published: New York IEEE 01.11.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accelerators
Artificial neural networks
Computational efficiency
Computational modeling
Computer architecture
Computing time
Convolutional neural network (CNN)
Convolutional neural networks
design space exploration (DSE)
Efficiency
Embedded systems
Field programmable gate arrays
field-programmable gate array (FPGA)-based accelerator
Gate arrays
Hardware
Neural networks
Optimization
pipeline
Pipelines
programming framework
Redundancy
redundancy elimination
Space exploration
System-on-chip
ISSN:0278-0070, 1937-4151
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, field-programmable gate arrays (FPGAs) have been widely used in the implementations of hardware accelerator for convolutional neural networks (CNNs). However, most of these existing accelerators are designed in the same idea as their ASIC counterparts, in which all operations from different layers are mapped to the same hardware units and working in a multiplexed way. This manner does not take full advantage of reconfigurability and customizability of FPGAs, resulting in a certain degree of computational efficiency degradation. In this paper, we propose a new architecture for FPGA-based CNN accelerator that maps all the layers to their own on-chip units and working concurrently as a pipeline. A comprehensive mapping and optimizing methodology based on establishing roofline model oriented optimization model is proposed, which can achieve maximum resource utilization as well as optimal computational efficiency. Besides, to ease the programming burden, we propose a design framework which can provide a one-stop function for developers to generate the accelerator with our optimizing methodology. We evaluate our proposal by implementing different modern CNN models on Xilinx Zynq-7020 and Virtex-7 690t FPGA platforms. Experimental results show that our implementations can achieve a peak performance of 910.2 GOPS on Virtex-7 690t, and 36.36 GOP/s/W energy efficiency on Zynq-7020, which are superior to the previous approaches.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0278-0070
1937-4151
DOI:10.1109/TCAD.2018.2857078