Survey of Deep Learning Accelerators for Edge and Emerging Computing
Open accessPublished version of a preprint
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 commercial edge processors utilize dataflow architectures. However, emerging non-von Neumann computing architectures have attracted the attention of 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. A future direction of the industry could be to implement state-of-the-art deep learning algorithms in emerging non-von Neumann computing paradigms for low-power computing on edge devices.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356 · see citing works
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
Rawat, W., & Wang, Z. (2017) · Neural Computation · doi:10.1162/neco_a_00990 · Cited by 3,503 · see citing works
Deep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540 · see citing works
Sequence-Level Knowledge Distillation
Kim, Y., & Rush, A. M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1139 · Cited by 836 · see citing works
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
Sun, Z., Yu, H., Song, X., Liu, R., Yang, Y., & Zhou, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.195 · Cited by 757 · see citing works
Bringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171 · see citing works
Khwa, W.-S., Chiu, Y.-C., Jhang, C.-J., Huang, S.-P., Lee, C.-Y., Wen, T.-H., Chang, F.-C., Yu, S.-M., Lee, T.-Y., & Chang, M.-F. (2022) · 2022 IEEE International Solid- State Circuits Conference (ISSCC) · doi:10.1109/isscc42614.2022.9731670 · Cited by 125 · see citing works
Hung, J.-M., Huang, Y.-H., Huang, S.-P., Chang, F.-C., Wen, T.-H., Su, C.-I., Khwa, W.-S., Lo, C.-C., Liu, R.-S., Hsieh, C.-C., et al. (2022) · 2022 IEEE International Solid- State Circuits Conference (ISSCC) · doi:10.1109/isscc42614.2022.9731715 · Cited by 125 · see citing works
Khaddam-Aljameh, R., Stanisavljevic, M., Fornt Mas, J., Karunaratne, G., Braendli, M., Liu, F., Singh, A., Müller, S. M., Egger, U., Petropoulos, A., et al. (2021) · 2021 Symposium on VLSI Circuits · doi:10.23919/vlsicircuits52068.2021.9492362 · Cited by 124 · see citing works
Neural inference at the frontier of energy, space, and time
Modha, D. S., Akopyan, F., Andreopoulos, A., Appuswamy, R., Arthur, J. V., Cassidy, A. S., Datta, P., DeBole, M. V., Esser, S. K., Otero, C. O., et al. (2023) · Science · doi:10.1126/science.adh1174 · Cited by 115 · see citing works
Flagged first, then by citations
- Authors
- Alam, S., Yakopcic, C., Wu, Q., Barnell, M., Khan, S., & Taha, T. M.
- Affiliations
- University of Dayton (US)
- United States Air Force Research Laboratory (US)
- Corresponding author
- Alam, Shahanur
- Taha, Tarek M.
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2024-07-29
- Volume
- 13
- Issue
- 15
- Pages
- 2988
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W4401067709
- Cited by
- 38
- References
- 11
- Citations by year
- 2026: 22 · 2025: 12 · 2024: 4
- FWCI
- 3.91
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- Preprints.org (acceptedVersion, cc-by)
- Funders
- Department of Electrical and Computer Engineering, University of Dayton
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Keywords
- deep learning accelerators, edge computing, neuromorphic computing, in-memory computing, dataflow architecture, non-von Neumann architecture, energy efficiency, energy-efficient computing, model compression, online training, CMOS fabrication
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
