Using the combinatorial optimization approach for DVS in high performance processors

Currently, in high performance computer systems, processors are faster and have vastly increased in performance and computational power. It is important for system designers to get an early estimation of power dissipation to meet the challenging methodologies for power dissipation reduction and optimization. In addition to the current design methodologies, the designer might need to consider the factors that affect the power and the interaction of these factors in practice. This paper presents a design technique for dynamic voltage scaling (DVS) for microprocessor's power dissipation control using the combinatorial design approach. The DVS unit dynamically alter processor's throughput for energy-efficiency by scaling down the supply voltage as well as clock frequency such that the actual delay of the chip meets the target performance. Whilst the combinatorial design is used to get an optimal interaction of the factors that affect the power to get optimal power dissipation estimation for the designer. Simulation and results are used to verify the theoretical background and optimization of the design approach which shows satisfactory results.

[1]  Chee Peng Lim,et al.  Application of Particle Swarm Optimization to uniform and variable strength covering array construction , 2012, Appl. Soft Comput..

[2]  Jeff Yu Lei,et al.  IPOG: A General Strategy for T-Way Software Testing , 2007, 14th Annual IEEE International Conference and Workshops on the Engineering of Computer-Based Systems (ECBS'07).

[3]  Phil McMinn,et al.  Search-based software test data generation: a survey: Research Articles , 2004 .

[4]  A. Jefferson Offutt,et al.  Combination testing strategies: a survey , 2005, Softw. Test. Verification Reliab..

[5]  Phil McMinn,et al.  Search‐based software test data generation: a survey , 2004, Softw. Test. Verification Reliab..

[6]  Kamal Zuhairi Zamli,et al.  A variable strength interaction test suites generation strategy using Particle Swarm Optimization , 2011, J. Syst. Softw..

[7]  A. Barrett,et al.  A Combinatorial Test Suite Generator for Gray-Box Testing , 2009, 2009 Third IEEE International Conference on Space Mission Challenges for Information Technology.

[8]  Hareton K. N. Leung,et al.  A survey of combinatorial testing , 2011, CSUR.

[9]  Bestoun S. Ahmed,et al.  Comparison of metahuristic test generation strategies based on interaction elements coverage criterion , 2011, 2011 IEEE Symposium on Industrial Electronics and Applications.

[10]  M.J. Flynn,et al.  Microprocessor design issues: thoughts on the road ahead , 2005, IEEE Micro.

[11]  S. M. Fakhraie,et al.  Reliability considerations in dynamic voltage and frequency scaling schemes , 2010, 5th International Conference on Design & Technology of Integrated Systems in Nanoscale Era.

[12]  Jin Xu,et al.  Research on Intelligent PID Control Strategy of Thermal Control Object , 2011, 2011 Third International Conference on Measuring Technology and Mechatronics Automation.

[13]  Mitsuhisa Sato,et al.  Profile-based optimization of power performance by using dynamic voltage scaling on a PC cluster , 2006, Proceedings 20th IEEE International Parallel & Distributed Processing Symposium.

[14]  R.W. Brodersen,et al.  A dynamic voltage scaled microprocessor system , 2000, IEEE Journal of Solid-State Circuits.

[15]  Lizy Kurian John,et al.  Complete System Power Estimation Using Processor Performance Events , 2012, IEEE Transactions on Computers.

[16]  Alan Hartman,et al.  Problems and algorithms for covering arrays , 2004, Discret. Math..

[17]  Myra B. Cohen,et al.  Covering arrays for efficient fault characterization in complex configuration spaces , 2004, IEEE Transactions on Software Engineering.

[18]  Petru Eles,et al.  On-line thermal aware dynamic voltage scaling for energy optimization with frequency/temperature dependency consideration , 2009, 2009 46th ACM/IEEE Design Automation Conference.

[19]  D E Shasha,et al.  Using combinatorial design to study regulation by multiple input signals. A tool for parsimony in the post-genomics era. , 2001, Plant physiology.

[20]  Yu-Wen Tung,et al.  Automating test case generation for the new generation mission software system , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).