Memristor-based approximated computation
The cessation of Moore's Law has limited further improvements in power efficiency. In recent years, the physical realization of the memristor has demonstrated a promising solution to ultra-integrated hardware realization of neural networks, which can be leveraged for better performance and powe...
Saved in:
Published in | Proceedings of the 2013 International Symposium on Low Power Electronics and Design pp. 242 - 247 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
Piscataway, NJ, USA
IEEE Press
04.09.2013
|
Series | ACM Conferences |
Subjects | |
Online Access | Get full text |
ISBN | 1479912352 9781479912353 |
DOI | 10.5555/2648668.2648729 |
Cover
Summary: | The cessation of Moore's Law has limited further improvements in power efficiency. In recent years, the physical realization of the memristor has demonstrated a promising solution to ultra-integrated hardware realization of neural networks, which can be leveraged for better performance and power efficiency gains. In this work, we introduce a power efficient framework for approximated computations by taking advantage of the memristor-based multilayer neural networks. A programmable memristor approximated computation unit (Memristor ACU) is introduced first to accelerate approximated computation and a memristor-based approximated computation framework with scalability is proposed on top of the Memristor ACU. We also introduce a parameter configuration algorithm of the Memristor ACU and a feedback state tuning circuit to program the Memristor ACU effectively. Our simulation results show that the maximum error of the Memristor ACU for 6 common complex functions is only 1.87% while the state tuning circuit can achieve 12-bit precision. The implementation of HMAX model atop our proposed memristor-based approximated computation framework demonstrates 22X power efficiency improvements than its pure digital implementation counterpart. |
---|---|
ISBN: | 1479912352 9781479912353 |
DOI: | 10.5555/2648668.2648729 |