Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation 2018
DOI: 10.1145/3229631.3235024
View full text
|
|
Share

Abstract: Convolutional Neural Networks (CNNs) are computationally intensive algorithms that currently require dedicated hardware to be executed. In the case of FPGA-Based accelerators, we point-out in this work the challenge of Multi-Operand Adders (MOAs) and their high resource utilization in an FPGA implementation of a CNN. To address this challenge, two optimization strategies, that rely on time-multiplexing and approximate computing, are investigated. At first glance, the two strategies looked promising to reduce …

Expand abstract

Search citation statements

Order By: Relevance

Paper Sections

0
0
0
0
0

Citation Types

0
5
0

Publication Types

Select...

Relationship

0
0

Authors

Journals