Instructions energy consumption on a heterogeneous multicore platform

Today more than ever, energy and power distribution on heterogeneous multicore platforms have immense influence on hardware and software architectures because of general tendencies towards energy efficient solutions. This paper provides an insight into the overall energy and power distribution on an ultra-low power heterogeneous multicore platform designed for hearing aids, especially focusing on energy dissipation that is caused by instructions execution. This research has been conducted in order to provide instruction set energy profile that could be used during instructions selection for both developer and compiler. Also, information about instructions energy consumption could be used for power profiling of entire firmware solutions, therefore providing valuable feedback to developers. Experiments have been conducted using customized Eclipse based Integrated Development Environment (IDE), the toolchain (Compiler, Assembler, Linker) developed for that particular target platform, and true RMS multimeter used for measurements. The outcome of the experiments has unequivocally confirmed that the obtained instruction set energy profile provides reliable information that could be used in various ways.

[1]  K. S. Gurumurthy,et al.  Instruction Level Power Analysis for Low Power VLSI Applications , 2013, 2013 6th International Conference on Emerging Trends in Engineering and Technology.

[2]  Gustavo Rau de Almeida Callou,et al.  Energy consumption and execution time estimation of embedded system applications , 2011, Microprocess. Microsystems.

[3]  Theodore Laopoulos,et al.  Energy Consumption Estimation in Embedded Systems , 2006, IEEE Transactions on Instrumentation and Measurement.

[4]  Jelena Kovacevic,et al.  An Empirical Methodology for Power Analysis of CMOS Integrated Circuits , 2017 .

[5]  Mike Tien-Chien Lee,et al.  Power analysis and low-power scheduling techniques for embedded DSP software , 1995 .

[6]  Th. Laopoulos,et al.  Measurements analysis of the software-related power consumption in microprocessors , 2003, IMTC 2003.

[7]  Miroslav Popovic,et al.  Data flow CAD tool for firniware development and power consumption estimation in multi-core hearing aids , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[8]  Theodore Laopoulos,et al.  Measurements analysis of the software-related power consumption in microprocessors , 2003, IEEE Transactions on Instrumentation and Measurement.

[9]  Sharad Malik,et al.  Power analysis of embedded software: a first step towards software power minimization , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[10]  Robert Oshana.  7 – Power Optimization Techniques Using DSP , 2006 .

[11]  R. Jacob Baker,et al.  CMOS Circuit Design, Layout, and Simulation , 1997 .

[12]  K. S. Gurumurthy,et al.  Software Power Analysis for Embedded DSP Software , 2014 .

[13]  Anantha P. Chandrakasan,et al.  Software energy profiling , 2002 .

[14]  Enrico Macii.  Energy-Aware SYstem-on-chip design of the HIPERLAN/2 standard , 2002 .

[15]  Alireza Ejlali,et al.  An Accurate Instruction-Level Energy Estimation Model and Tool for Embedded Systems , 2013, IEEE Transactions on Instrumentation and Measurement.

[16]  Hermann de Meer,et al.  Evaluating and modeling power consumption of multi-core processors , 2012, 2012 Third International Conference on Future Systems: Where Energy, Computing and Communication Meet (e-Energy).

[17]  Miroslav Popovic,et al.  Energy Consumption Estimation for Embedded Applications , 2016 .

[18]  Trevor Mudge,et al.  Challenges for architectural level power modeling , 2002 .