An investigation on FPGA based energy profiling of multi-core embedded architectures

Power and energy profiling of multi-core embedded SoC designs is a daunting task due to the lack of fine grain accurate and high sampling rate monitoring infrastructures. Furthermore, shared components used in common by multiple processing cores, make these designs difficult to analyze consumption of concurrent threads. FPGA development boards are currently used to implement multi-core SoC prototypes in order to validate them on real hardware and to perform thoroughly performance profiling. In this paper, we investigate the capacity of FPGA designs to profile the power consumption and energy usage of multi-core embedded architectures and application benchmarks running on them.

[1]  Jason Helge Anderson,et al.  Low-cost hardware profiling of run-time and energy in FPGA embedded processors , 2011, ASAP 2011 - 22nd IEEE International Conference on Application-specific Systems, Architectures and Processors.

[2]  Rabie Ben Atitallah,et al.  An Efficient Framework for Power-Aware Design of Heterogeneous MPSoC , 2013, IEEE Transactions on Industrial Informatics.

[3]  Viktor K. Prasanna,et al.  Rapid energy estimation of computations on FPGA based soft processors , 2004, IEEE International SOC Conference, 2004. Proceedings..

[4]  Cecile Belleudy,et al.  Power Estimation Method Based on Real Measurements for Processor-Based Designs on FPGA , 2014, 2014 International Conference on Computational Science and Computational Intelligence.

[5]  Christos-Savvas Bouganis,et al.  High-level power and performance estimation of FPGA-based soft processors and its application to design space exploration , 2013, J. Syst. Archit..

[6]  Yuichiro Shibata,et al.  Power Performance Profiling of 3-D Stencil Computation on an FPGA Accelerator for Efficient Pipeline Optimization , 2016, CARN.

[7]  A. Gil-de-Castro,et al.  FPGA-based embedded system architecture for power quality measurements , 2012, 2012 IEEE 15th International Conference on Harmonics and Quality of Power.

[8]  Jason G. Tong,et al.  Profiling Tools for FPGA-Based Embedded Systems: Survey and Quantitative Comparison , 2008, J. Comput..

[9]  Rainer Leupers,et al.  Low-Cost Hardware Infrastructure for Runtime Thread Level Energy Accounting , 2016, ARCS.