Version 1
: Received: 30 June 2024 / Approved: 1 July 2024 / Online: 1 July 2024 (11:20:49 CEST)
How to cite:
Alam, M. S.; Yakopcic, C.; Wu, Q.; Barnell, M.; Khan, S.; Taha, T. M. Survey of Deep Learning Accelerators for Edge and Emerging Computing. Preprints2024, 2024070025. https://doi.org/10.20944/preprints202407.0025.v1
Alam, M. S.; Yakopcic, C.; Wu, Q.; Barnell, M.; Khan, S.; Taha, T. M. Survey of Deep Learning Accelerators for Edge and Emerging Computing. Preprints 2024, 2024070025. https://doi.org/10.20944/preprints202407.0025.v1
Alam, M. S.; Yakopcic, C.; Wu, Q.; Barnell, M.; Khan, S.; Taha, T. M. Survey of Deep Learning Accelerators for Edge and Emerging Computing. Preprints2024, 2024070025. https://doi.org/10.20944/preprints202407.0025.v1
APA Style
Alam, M. S., Yakopcic, C., Wu, Q., Barnell, M., Khan, S., & Taha, T. M. (2024). Survey of Deep Learning Accelerators for Edge and Emerging Computing. Preprints. https://doi.org/10.20944/preprints202407.0025.v1
Chicago/Turabian Style
Alam, M. S., Saimon Khan and Tarek M. Taha. 2024 "Survey of Deep Learning Accelerators for Edge and Emerging Computing" Preprints. https://doi.org/10.20944/preprints202407.0025.v1
Abstract
The unprecedented progress in Artificial Intelligence (AI), particularly in deep learning algorithms with ubiquitous internet connected smart devices, has created a high demand for AI computing on the edge devices. This review studied commercially available edge processors, and the processors that are still in industrial research stages. We categorized state-of-the-art edge processors based on the underlying architecture, such as dataflow, neuromorphic, and Processing in-Memory (PIM) architecture. The processors are analyzed based on their performance, chip area, energy efficiency, and application domains. The supported programming frameworks, model compression, data precision, and the CMOS fabrication process technology are discussed. Currently, most of the commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the industry in recent years. Neuromorphic processors are highly efficient for performing computation with fewer synaptic operations, and several neuromorphic processors offer online training for secured and personalized AI applications. This review found that the PIM processors show significant energy efficiency and consume less power compared to dataflow and neuromorphic processors. The future direction of the industry would be to implement state-of-the-art deep learning algorithms in emerging non-Von Neumann computing paradigms for low power computing on the edge devices.
Keywords
AI Accelerator, AI Frameworks, Deep Learning, Edge Computing, Low Power Applications, Quantization, PIM or CIM Computing, Neuromorphic Computing.
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.