Improving Reconfigurable Hardware Energy Efficiency and Robustness via DVFS-Scaled Homogeneous MP-SoC

This paper presents the study of Dynamic Voltage and Frequency Scaling (DVFS) technique applied to an existing multi-core architecture composed of 9 computational nodes interconnected by a hierarchical Network-on-Chip. The architecture was synthesized and characterized in area/power utilizing 65nm standard cell technology. For the analysis of the achievable energy/power saving, a representative algorithm from wireless communications was utilized as test case. Energy and power reduction results achieved with DVFS were then compared to the ones obtainable via clock gating. The results show that DVFS guarantees higher energy savings than clock gating. Moreover, when considering power consumption DVFS improves the system performance by a factor of 3 when compared to clock gating, improving hardware robustness to soft errors related to power integrity phenomena.

[1]  Jari Nurmi,et al.  Energy-Efficient Fast Fourier Transforms for Cognitive Radio Systems , 2010, IEEE Micro.

[2]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[3]  Ryan W. Apperson,et al.  AsAP: An Asynchronous Array of Simple Processors , 2008, IEEE Journal of Solid-State Circuits.

[4]  Alexander M. Wyglinski,et al.  An Efficient Implementation of NC-OFDM Transceivers for Cognitive Radios , 2006, 2006 1st International Conference on Cognitive Radio Oriented Wireless Networks and Communications.

[5]  J. Markel,et al.  FFT pruning , 1971 .

[6]  Jari Nurmi,et al.  Homogeneous MPSoC as baseband signal processing engine for OFDM systems , 2010, 2010 International Symposium on System on Chip.