Managing performance and efficiency of a processor

The performance of a processor generally means how fast it can execute a task. For a given architecture we can measure the size of a task as the number of clock cycles it will take to execute. Then clock frequency (f) will determine the execution time. Normally, the frequency can be raised if the supply voltage Vdd is increased. This, however, increases the power and energy used. We introduce a new measure, cycle efficiency (η) as cycles per joule that gives the rate of computational work per unit energy. Similar to f, η is also a function of Vdd. We provide a method of characterizing a processor in terms of its f and η versus Vdd characteristics. Intel Pentium M processor with an assumed 90nm CMOS PTM (predictive technology model) is used as an example. For a demonstration of performance and energy management, we consider a program that executes in 1.8 billion clock cycles. At the nominal operating supply of 1.2V we have f = 1.8GHz and η = 15 megacycles/joule. The program executes in 1 second and uses 120 joules. For operation at 0.6V, f = 277MHz and η = 70 megacycles/joule, resulting in a run time of 6.5 seconds and consumption of 25 joules. We also find a subthreshold voltage extreme of 200mV, f = 54.5MHz and η = 660 megacycles/joule. Now the program will take 33 seconds but will consume only 2.27 joules. Thus, using cycle efficiency and clock frequency one can manage the time and energy performances according to the requirements of a computing task.

[1]  Sharad Malik,et al.  Dynamic power management for microprocessors: a case study , 1997, Proceedings Tenth International Conference on VLSI Design.

[2]  Mark Horowitz,et al.  Energy dissipation in general purpose microprocessors , 1996, IEEE J. Solid State Circuits.

[3]  Vishwani D. Agrawal,et al.  Ultra Low Energy CMOS Logic Using Below-Threshold Dual-Voltage Supply , 2011, J. Low Power Electron..

[4]  Yu Cao,et al.  New Generation of Predictive Technology Model for Sub-45 nm Early Design Exploration , 2006, IEEE Transactions on Electron Devices.

[5]  Daeyeon Kim,et al.  The Phoenix Processor: A 30pW platform for sensor applications , 2008, 2008 IEEE Symposium on VLSI Circuits.

[6]  Vladimir Stojanovic,et al.  Digital System Clocking: High-Performance and Low-Power Aspects , 2003 .

[7]  Naehyuck Chang,et al.  Energy-Optimal Dynamic Thermal Management: Computation and Cooling Power Co-Optimization , 2010, IEEE Transactions on Industrial Informatics.

[8]  Anantha Chandrakasan,et al.  Sub-threshold Design for Ultra Low-Power Systems , 2006, Series on Integrated Circuits and Systems.

[9]  Kyungseok Kim,et al.  Ultra Low Power CMOS Design , 2011 .

[10]  V. Agrawal,et al.  Dual voltage design for minimum energy using gate slack , 2011, 2011 IEEE International Conference on Industrial Technology.

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

[12]  Bo Zhai,et al.  Performance and Variability Optimization Strategies in a Sub-200mV, 3.5pJ/inst, 11nW Subthreshold Processor , 2007, 2007 IEEE Symposium on VLSI Circuits.

[13]  Anoop Gupta,et al.  The SPLASH-2 programs: characterization and methodological considerations , 1995, ISCA.

[14]  Victor V. Zyuban,et al.  Optimization of high-performance superscalar architectures for energy efficiency , 2000, ISLPED'00: Proceedings of the 2000 International Symposium on Low Power Electronics and Design (Cat. No.00TH8514).

[15]  David Blaauw,et al.  Energy efficient near-threshold chip multi-processing , 2007, Proceedings of the 2007 international symposium on Low power electronics and design (ISLPED '07).

[16]  David Blaauw.  Power management issues in high performance processor design , 1999, Proceedings IEEE Alessandro Volta Memorial Workshop on Low-Power Design.

[17]  David J. Lilja,et al.  Measuring computer performance : A practitioner's guide , 2000 .

[18]  Meeta Sharma Gupta,et al.  System level analysis of fast, per-core DVFS using on-chip switching regulators , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[19]  Michael Andrew Hicks.  Energy Efficient Branch Prediction , 2010 .

[20]  Vishwani D. Agrawal,et al.  A Tutorial on Battery Simulation - Matching Power Source to Electronic System , 2010 .

[21]  David A. Patterson,et al.  Computer Organization and Design, Fourth Edition, Fourth Edition: The Hardware/Software Interface (The Morgan Kaufmann Series in Computer Architecture and Design) , 2008 .

[22]  Vishwani D. Agrawal,et al.  Energy source lifetime optimization for a digital system through power management , 2011, 2011 IEEE 43rd Southeastern Symposium on System Theory.

[23]  Vishwani D. Agrawal,et al.  Subthreshold voltage high-k CMOS devices have lowest energy and high process tolerance , 2011, 2011 IEEE 43rd Southeastern Symposium on System Theory.

[24]  A. R. Newton,et al.  Alpha-power law MOSFET model and its applications to CMOS inverter delay and other formulas , 1990 .

[25]  David A. Patterson,et al.  Computer Organization & Design: The Hardware/Software Interface , 1993 .

[26]  Deborah A. Wallach,et al.  Power Evaluation of Itsy Version 2.3 , 2000 .

[27]  Victor V. Zyuban,et al.  The energy complexity of register files , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[28]  Margaret Martonosi,et al.  Run-time power estimation in high performance microprocessors , 2001, ISLPED '01.

[29]  Daniele Folegnani,et al.  Reducing Power Consumption of the Issue Logic , 2000 .

[30]  Karthick Rajamani,et al.  Thermal response to DVFS: analysis with an Intel Pentium M , 2007, Proceedings of the 2007 international symposium on Low power electronics and design (ISLPED '07).

[31]  Sarma B. K. Vrudhula,et al.  Performance Optimal Online DVFS and Task Migration Techniques for Thermally Constrained Multi-Core Processors , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[32]  Lawrence T. Clark,et al.  Dynamic Voltage Scaling with the XScale Embedded Microprocessor , 2008 .

[33]  Miodrag Potkonjak,et al.  Function-level power estimation methodology for microprocessors , 2000, DAC.

[34]  Vishwani D. Agrawal,et al.  True Minimum Energy Design Using Dual Below-Threshold Supply Voltages , 2011, 2011 24th Internatioal Conference on VLSI Design.

[35]  N.G. Santiago,et al.  High-level optimization for low power consumption on microprocessor-based systems , 2007, 2007 50th Midwest Symposium on Circuits and Systems.

[36]  Muralidharan Venkatasubramanian,et al.  Energy Efficiency and Process Variation Tolerance of 45 nm Bulk and High-k CMOS Devices , 2011 .

[37]  Chris J. Bleakley,et al.  Power Consumption Characterisation of the Texas Instruments TMS320VC5510 DSP , 2005, PATMOS.

[38]  Gary K. Yeap,et al.  Practical Low Power Digital VLSI Design , 1997 .

[39]  Vishwani D. Agrawal,et al.  Minimum energy CMOS design with dual subthreshold supply and multiple logic-level gates , 2011, 2011 12th International Symposium on Quality Electronic Design.

[40]  David Blaauw,et al.  Near-Threshold Computing: Reclaiming Moore's Law Through Energy Efficient Integrated Circuits , 2010, Proceedings of the IEEE.

[41]  Ravishankar Rao,et al.  Efficient online computation of core speeds to maximize the throughput of thermally constrained multi-core processors , 2008, ICCAD 2008.

[42]  B. M. Gordon,et al.  Supply and threshold voltage scaling for low power CMOS , 1997, IEEE J. Solid State Circuits.

[43]  James B. Kuo,et al.  Low-voltage CMOS VLSI circuits , 1999 .

[44]  Srilatha Manne,et al.  Power and performance tradeoffs using various caching strategies , 1998, Proceedings. 1998 International Symposium on Low Power Electronics and Design (IEEE Cat. No.98TH8379).

[45]  Alain J. Martin,et al.  ET 2 : a metric for time and energy efficiency of computation , 2002 .

[46]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).