Energy-Efficient Approximate Edge Inference Systems
ACM Transactions on Embedded Computing Systems · 31.07.2023 · 22 (4) · 1-50
DOI: 10.1145/3589766 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 24.07.2023. Verfasst von Soumendu Kumar Ghosh und 2 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 112 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Center for Brain-inspired Computing Enabling Autonomous Intelligence, Joint University Microelectronics Program, Semiconductor Research Corporation.
Abstract (Originalsprache)
The rapid proliferation of the Internet of Things and the dramatic resurgence of artificial intelligence based application workloads have led to immense interest in performing inference on energy-constrained edge devices. Approximate computing (a design paradigm that trades off a small degradation in application quality for disproportionate energy savings) is a promising technique to enable energy-efficient inference at the edge. This article introduces the concept of an approximate edge inference system ( AxIS ) and proposes a systematic methodology to perform joint approximations between different subsystems in a deep neural network (DNN)-based edge inference system, leading to significant energy benefits compared to approximating individual subsystems in isolation. We use a smart camera system that executes various DNN-based image classification and object detection applications to illustrate how the sensor, memory, compute, and communication subsystems can all be approximated synergistically. We demonstrate our proposed methodology using two variants of a smart camera system: (a) Cam Edge , where the DNN is executed locally on the edge device, and (b) Cam Cloud , where the edge device sends the captured image to a remote cloud server that executes the DNN. We have prototyped such an approximate inference system using an Intel Stratix IV GX-based Terasic TR4-230 FPGA development board. Experimental results obtained using six large DNNs and four compact DNNs running image classification applications demonstrate significant energy savings (≈ 1.6× -4.7× for large DNNs and ≈ 1.5× -3.6× for small DNNs), for minimal (
Förderung
- Center for Brain-inspired Computing Enabling Autonomous Intelligence
- Joint University Microelectronics Program
- Semiconductor Research Corporation
- Defense Advanced Research Projects Agency
Zitieren
APA
Ghosh, S. K., Raha, A., & Raghunathan, V. (2023). Energy-Efficient Approximate Edge Inference Systems. ACM Transactions on Embedded Computing Systems, 22(4), 1-50. https://doi.org/10.1145/3589766
Vancouver
Ghosh SK, Raha A, Raghunathan V. Energy-Efficient Approximate Edge Inference Systems. ACM Transactions on Embedded Computing Systems. 2023;22(4):1-50. doi:10.1145/3589766
BibTeX
@article{Ghosh2023,
author = {Ghosh, Soumendu Kumar and Raha, Arnab and Raghunathan, Vijay},
title = {Energy-Efficient Approximate Edge Inference Systems},
journal = {ACM Transactions on Embedded Computing Systems},
year = {2023},
volume = {22},
number = {4},
pages = {1--50},
doi = {10.1145/3589766}
}
EUVIMED