LSTM Hardware Inference Accelerator for LiteRT
IEEE Transactions on Circuits and Systems I: Regular Papers · 2026-02 · 73 (2) · 1052-1064
DOI: 10.1109/tcsi.2025.3609633 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems I: Regular Papers, 2026-02. Verfasst von G. Mannes und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
The efficient deployment of Recurrent Neural Networks (RNNs), particularly long short-term memory (LSTM) architectures, on edge devices has become increasingly important due to their ability to model nonlinear time-variant dynamics. However, the computational demands of LSTM inference often exceed the capabilities of resource-constrained microcontroller-based IoT devices. Efficient mapping of computational load onto hardware and software resources is a key challenge for improving performance while maintaining low power and a small area footprint. This paper presents a hardware-software framework that accelerates LSTM inference on edge devices by combining a modified LiteRT (formerly TensorFlow Lite) model running on a microcontroller (MCU) with a dedicated LSTM engine in a Neural Processing Unit (NPU) accelerator. To evaluate trade-offs between accuracy, latency, and energy efficiency, we introduce an LSTM benchmark suite for ultra-low-power tiny ML systems. Using this framework, experiments on various LiteRT-based LSTM architectures demonstrate up to 300x speedup compared to software-only implementations. For instance, the runtime for the HAR classification task is reduced from 1.8 seconds to just 6 milliseconds.
Zitieren
APA
Mannes, G., Manor, E., & Greenberg, S. (2026). LSTM Hardware Inference Accelerator for LiteRT. IEEE Transactions on Circuits and Systems I: Regular Papers, 73(2), 1052-1064. https://doi.org/10.1109/tcsi.2025.3609633
Vancouver
Mannes G, Manor E, Greenberg S. LSTM Hardware Inference Accelerator for LiteRT. IEEE Transactions on Circuits and Systems I: Regular Papers. 2026;73(2):1052-1064. doi:10.1109/tcsi.2025.3609633
BibTeX
@article{Mannes2026,
author = {Mannes, G. and Manor, E. and Greenberg, S.},
title = {LSTM Hardware Inference Accelerator for LiteRT},
journal = {IEEE Transactions on Circuits and Systems I: Regular Papers},
year = {2026},
volume = {73},
number = {2},
pages = {1052--1064},
doi = {10.1109/tcsi.2025.3609633}
}
EUVIMED