Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918459519008768 |
|---|---|
| author | Qian, Chao Ling, Tianheng Schiele, Gregor |
| author_facet | Qian, Chao Ling, Tianheng Schiele, Gregor |
| contents | Long Short-term Memory Networks (LSTMs) are a vital Deep Learning technique suitable for performing on-device time series analysis on local sensor data streams of embedded devices. In this paper, we propose a new hardware accelerator design for LSTMs specially optimised for resource-scarce embedded Field Programmable Gate Arrays (FPGAs). Our design improves the execution speed and reduces energy consumption compared to related work. Moreover, it can be adapted to different situations using a number of optimisation parameters, such as the usage of DSPs or the implementation of activation functions. We present our key design decisions and evaluate the performance. Our accelerator achieves an energy efficiency of 11.89 GOP/s/W during a real-time inference with 32873 samples/s. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19293 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design Qian, Chao Ling, Tianheng Schiele, Gregor Hardware Architecture Long Short-term Memory Networks (LSTMs) are a vital Deep Learning technique suitable for performing on-device time series analysis on local sensor data streams of embedded devices. In this paper, we propose a new hardware accelerator design for LSTMs specially optimised for resource-scarce embedded Field Programmable Gate Arrays (FPGAs). Our design improves the execution speed and reduces energy consumption compared to related work. Moreover, it can be adapted to different situations using a number of optimisation parameters, such as the usage of DSPs or the implementation of activation functions. We present our key design decisions and evaluate the performance. Our accelerator achieves an energy efficiency of 11.89 GOP/s/W during a real-time inference with 32873 samples/s. |
| title | Energy Efficient LSTM Accelerators for Embedded FPGAs through Parameterised Architecture Design |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2604.19293 |