Compiling KB-sized machine learning models to tiny IoT devices
Abstract
Recent advances in machine learning (ML) have produced KiloByte-size models that can directly run on constrained IoT devices. This approach avoids expensive communication between IoT devices and the cloud, thereby enabling energy-efficient real-time analytics. However, ML models are expressed typically in floating-point, and IoT hardware typically does not support floating-point. Therefore, running these models on IoT devices requires simulating IEEE-754 floating-point using software, which is very inefficient.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
SEEDoT allows the compiler to compile KB size machine learning models for targeting tiny microcontrollers such as Arduino.
“The SEEDoT allows the compiler to compile KB size machine learning models for targeting tiny microcontrollers such as Arduino.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Gopinath et al., 2019
A compilation technique is developed to reduce search space for any crucial parameter for the fixed-point code.
“To do that, a compilation technique is developed to reduce search space for any crucial parameter for the fixed-point code.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Gopinath et al., 2019
Gopinath et al. (2019) presented a domain-specific language SEEDoT to infer machine learning algorithms for tiny devices.
“In (Gopinath et al., 2019), a domainspecific language -SEEDoT is presented to infer machine learning algorithms for tiny devices.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Gopinath et al., 2019
Cited by
Sorted by citations
A review on TinyML: State-of-the-art and prospects
Ray, P. P. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.11.019 · Cited by 460 · see citing works
CrypTFlow: Secure TensorFlow Inference
Kumar, N., Rathee, M., Chandran, N., Gupta, D., Rastogi, A., & Sharma, R. (2020) · 2020 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40000.2020.00092 · Cited by 245 · see citing works
Self-citationMachine Learning on Mainstream Microcontrollers
Sakr, F., Bellotti, F., Berta, R., & De Gloria, A. (2020) · Sensors · doi:10.3390/s20092638 · Cited by 109 · see citing works
An Evolving TinyML Compression Algorithm for IoT Environments Based on Data Eccentricity
Signoretti, G., Silva, M., Andrade, P., Silva, I., Sisinni, E., & Ferrari, P. (2021) · Sensors · doi:10.3390/s21124153 · Cited by 73 · see citing works
DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Tabanelli, E., Tagliavini, G., & Benini, L. (2021) · arXiv · doi:10.48550/arxiv.2107.09448 · Cited by 36 · see citing works
- Authors
- Gopinath, S., Ghanathe, N., Seshadri, V., & Sharma, R.
- Affiliations
- Microsoft Research (India) (IN)
- Venue
- Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation
- Publisher
- ACM
- Published
- 2019-06-08
- Pages
- 79-95
- ISSN
- 1531-7102 (ISSN-L)
- OpenAlex
- W2902032143
- Cited by
- 92
- References
- 0
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 4 · 2023: 26 · 2022: 21 · 2021: 22 · 2020: 8 · 2019: 2
- FWCI
- 13.35
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Numerical Methods and Algorithms
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Keywords
- model compression, IoT devices, resource-constrained devices, IEEE 754, program compilation, edge computing
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
