A_Technique_for_Approximate_Communication_in_Network_on_Chips_for_Image_Classification.pdf (986.08 kB)
Download fileA Technique for Approximate Communication in Network-on-Chips for Image Classification
preprint
posted on 31.08.2021, 20:53 by Yuechen ChenYuechen Chen, Shanshan LiuShanshan Liu, Fabrizio Lombardi, Ahmed LouriApproximation is an effective technique for reducing power consumption and latency of on-chip communication in many computing applications. However, existing approximation techniques either achieve modest improvements in these metrics or require retraining after approximation, such when convolutional neural networks (CNNs) are employed. Since classifying many images introduces intensive on-chip communication, reductions in both network latency and power consumption are highly desired. In this paper, we propose an approximate communication technique (ACT) to improve the efficiency of on-chip communications for image classification applications. The proposed technique exploits the error-tolerance of the image classification process to reduce power consumption and latency of on-chip communications, resulting in better overall performance for image classification computation. This is achieved by incorporating novel quality control and data approximation mechanisms that reduce the packet size. In particular, the proposed quality control mechanisms identify the error-resilient variables and automatically adjust the error thresholds of the variables based on the image classification accuracy. The proposed data approximation mechanisms significantly reduce packet size when the variables are transmitted. The proposed technique reduces the number of flits in each data packet as well as the on-chip communication, while maintaining an excellent image classification accuracy. The cycle-accurate simulation results show that ACT achieves 23% in network latency reduction and 24% in dynamic power reduction compared to the existing approximate communication technique with less than 0.99% classification accuracy loss.
Funding
CCF-1953961
CCF-1812467
CCF-1812495
CCF-1953980
History
Email Address of Submitting Author
yuechen@gwu.eduORCID of Submitting Author
https://orcid.org/0000-0001-6671-8443Submitting Author's Institution
Department of Electrical and Computer Engineering, School of Engineering and Applied Science, The George Washington UniversitySubmitting Author's Country
United States of AmericaUsage metrics
Read the peer-reviewed publication
in IEEE Transactions on Emerging Topics in Computing