IMPROVED SORTING METHODOLOGY OF DATA-PROCESSING INSTRUCTIONS
DOI:
https://doi.org/10.47839/ijc.10.1.736Keywords:
Power consumption, ARM7TDMI, Data-processing, instructions, neural networks, sorting training set, power estimation.Abstract
An improved classification methodology for sorting data-processing instructions for ARM7TDMI CPU core is presented in this paper. Main discussion here is related to the process of creating appropriate training sets for neural network (NN) based estimation of power consumption. We have proposed instructions’ sorting methodology according to the binary instruction representation and the resources being used for the overall system model. Thus separate instructions groups are obtained for NN-based estimation of power consumption. Experimental results of the proposed method confirm successful usage of this sorting methodology for providing higher accuracy estimation of power consumption.References
Nikolaidis S., Chatzigeorgiou A., and Laopoulos Th. Developing an Environment for Embedded Software Energy Estimation. Computers, Standards and Interfaces, Vol. 28, N. 2, 2005.
Kavvadias N., Neofotistos P., Nikolaidis S., Kosmatopoulos C., and Laopoulos Th. Measurements Analysis of the Software-Related Power Consumption of Microprocessors. IEEE Transactions on Instrumentation and Measurement, Vol. 53, N. 4, 2004.
Carlo Brandolese, William Fornaciari, and Fabio Salice. Ultra Low-Power Electronics and Design, chapter Source-Level Models for Software Power Optimization, pages 156–171. Politecnico di Torino, Italy, 2004.
M. F. Jacome, A. Ramachandran. Power Aware Embedded Computing. Embedded Systems Handbook Zurawski, R. (ed.) CRC Taylor & Francis, 2006, pp. 16-1 – 16-17.
A. Borovyi, V. Konstantakos, V. Kochan et al. Analysis of CPU’s instructions energy consumption device circuits. Proceedings of the fourth IEEE international workshop on Intelligent Data Acquisition and Advancing Computing Systems (IDAACS 2007), Dortmund, Germany, September 9–11, 2007. pp. 42-47. – ISBN 978-1-4244-1347-8
A. Borovyi, V. Konstantakos, V. Kochan et al. Using Neural Network for the Evaluation of Power Consumption of Instructions Execution. Proceedings of the Fifth International Instrumentation and Measurement Technology Conference (I2MTC’2008). Vancouver Island, Victoria, British Columbia, Canada, May 12-15, 2008. pp. 676-681.
ARM Limited, editor. ARM Architecture Reference Manual. Number ARM DDI 0100I. ARM Limited, 2007.
S. Segars. ARM7TDMI Power Consumption. IEEE MICRO, 17(4):12–19, July– Aug. 1997.
A. Borovyi, O. Havryshok, V. Kochan, Z. Dombrovsky. Development problems of the CPU power consumptionm model. Proceedings of the 10th International Scientific Conference “Modern Information and Electronic Technologies”, May 18-22 2009, Ukraine. Vol. 1, p. 157. (in Ukrainian).
Nikolaidis S., Kavvadias N., Laopoulos T., Bisdounis L., Blionas S. Instruction-level energy modeling for pipelined processors. Journal of Embedded Computing (special issue on Low-Power Design), Cambridge International Science Publishing (CISP), No. 3, 2004.
K. Hornik, M. Stinchcombe, and H. White. Multilayer feedforward networks are universal approximators. Neural Networks. (No. 2) (1989). pp. 359-366.
Simon Haykin. Neural Networks and Learning Machines. 3rd Edition, Prentice Hall, 2008. 936 p.
V. Golovko. Neural Networks: training, models and applications. Radiotechnika. Moscow, 2001, P. 256. (In Russian).
D. Rumelhart, G. Hinton, R. Williams. Learning representation by back-propagation errors. Nature. (323) (1986) pp. 533-536.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
