A Unified Parallel CORDIC-Based Hardware Architecture for LSTM Network Acceleration
IEEE Transactions on Computers · 2023-10 · 72 (10) · 2752-2766
DOI: 10.1109/tc.2023.3268400 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2023-10. Verfasst von Nadya A. Mohamed und 1 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Deep Neural Networks (DNNs) have recently become the standard tool for solving various practical problems in a wide range of applications with state-of-the-art performance. Recurrent Neural Networks (RNNs) such as Long Short-Term Memory (LSTM) are a subset of DNNs with fully connected single or multi-layer networks. The complex neurons and internal states of LSTM networks enable them to build a memory of events, making them ideal for time series applications. Despite the great potential of LSTM networks, their heterogeneous operations and computational resource requirements create a vast gap when it comes to the fast processing time required in real-time applications using low-power, low-cost edge devices. This work proposes a novel hardware architecture that combines serial-parallel computation with matrix algebra concepts and efficient low-power computer arithmetics for LSTM network acceleration. The hardware is based on a systolic ring of outer-product-based processing elements (PEs) and a reusable single activation function block (AFB). PEs and AFB are implemented using the coordinate rotation digital computer algorithm (CORDIC) in the linear and hyperbolic modes. Unlike most approaches, the proposed hardware can be configured to perform recurrent and non-recurrent fully connected layers (FC) computations, making it suitable for various low-power edge applications. The architecture is validated on the Xilinx PYNQ-Z1 development board using an open-source time series dataset. The implemented design achieves $\text{114} \mu \text{s}$ 114 μ s average latency and $\text{1.8 GOPS}$ 1.8 GOPS throughput. The proposed design's low latency and $\text{0.438 W}$ 0.438 W power consumption makes it suitable for resource-constrained edge platforms.
Förderung
- National Science Foundation
Zitieren
APA
Mohamed, N. A., & Cavallaro, J. R. (2023). A Unified Parallel CORDIC-Based Hardware Architecture for LSTM Network Acceleration. IEEE Transactions on Computers, 72(10), 2752-2766. https://doi.org/10.1109/tc.2023.3268400
Vancouver
Mohamed NA, Cavallaro JR. A Unified Parallel CORDIC-Based Hardware Architecture for LSTM Network Acceleration. IEEE Transactions on Computers. 2023;72(10):2752-2766. doi:10.1109/tc.2023.3268400
BibTeX
@article{Mohamed2023,
author = {Mohamed, Nadya A. and Cavallaro, Joseph R.},
title = {A Unified Parallel CORDIC-Based Hardware Architecture for LSTM Network Acceleration},
journal = {IEEE Transactions on Computers},
year = {2023},
volume = {72},
number = {10},
pages = {2752--2766},
doi = {10.1109/tc.2023.3268400}
}
EUVIMED