System-wide energy optimization for multiple DVS components and real-time tasks

Most dynamic voltage and frequency scaling (DVS) techniques adjust only CPU parameters; however, recent embedded systems provide multiple adjustable clocks which can be independently tuned. When considering multiple components, energy optimal frequencies depend on task set characteristics such as the number of CPU and memory access cycles. In this work, we propose a realistic energy model considering multiple components with individually adjustable frequencies such as CPUs, system bus and memory, and related task set characteristics. The model is validated on a real platform and shows less than 2% relative error compared to measured values. Based on the proposed energy model, we present an optimal static frequency assignment scheme for multiple DVS components to schedule a set of periodic real-time tasks. We simulate the energy gain of the proposed scheme compared to other DVS schemes for various task and system configurations, showing up to a 20% energy reduction. We also experimentally verify energy savings of the proposed scheme on a real hardware platform.

[1]  Luca Benini,et al.  Cycle-accurate simulation of energy consumption in embedded systems , 1999, DAC '99.

[2]  Vinay Devadas,et al.  Real-Time Dynamic Power Management through Device Forbidden Regions , 2008, 2008 IEEE Real-Time and Embedded Technology and Applications Symposium.

[3]  Roy H. Campbell,et al.  Context switch overheads on mobile device platforms , 2007 .

[4]  Masato Edahiro,et al.  FIDES: An advanced chip multiprocessor platform for secure next generation mobile terminals , 2008, ACM Trans. Embed. Comput. Syst..

[5]  Tei-Wei Kuo,et al.  Multiprocessor energy-efficient scheduling with task migration considerations , 2004, Proceedings. 16th Euromicro Conference on Real-Time Systems, 2004. ECRTS 2004..

[6]  Steve Goddard,et al.  Integrated Device Scheduling and Processor Voltage Scaling for System-wide Energy Conservation , 2005 .

[7]  Xiliang Zhong,et al.  System-Wide Energy Minimization for Real-Time Tasks: Lower Bound and Approximation , 2006, 2006 IEEE/ACM International Conference on Computer Aided Design.

[8]  Marco Caccamo,et al.  Toward the Predictable Integration of Real-Time COTS Based Systems , 2007, 28th IEEE International Real-Time Systems Symposium (RTSS 2007).

[9]  Flavius Gruian.  Hard real-time scheduling for low-energy using stochastic data and DVS processors , 2001, ISLPED '01.

[10]  David C. Snowdon,et al.  Accurate on-line prediction of processor and memoryenergy usage under voltage scaling , 2007, EMSOFT '07.

[11]  David C. Snowdon,et al.  Koala: a platform for OS-level power management , 2009, EuroSys '09.

[12]  Massoud Pedram,et al.  Power-aware scheduling and dynamic voltage setting for tasks running on a hard real-time system , 2006, Asia and South Pacific Conference on Design Automation, 2006..

[13]  Lui Sha,et al.  System-Wide Energy Optimization for Multiple DVS Components and Real-Time Tasks , 2010, ECRTS.

[14]  Giuseppe Lipari,et al.  Speed modulation in energy-aware real-time systems , 2005, 17th Euromicro Conference on Real-Time Systems (ECRTS'05).

[15]  Rami G. Melhem,et al.  Determining optimal processor speeds for periodic real-time tasks with different power characteristics , 2001, Proceedings 13th Euromicro Conference on Real-Time Systems.

[16]  Luca Benini,et al.  Dynamic voltage scaling and power management for portable systems , 2001, Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232).

[17]  Meng Wang,et al.  Overhead-Aware System-Level Joint Energy and Performance Optimization for Streaming Applications on Multiprocessor Systems-on-Chip , 2008, 2008 Euromicro Conference on Real-Time Systems.

[18]  Luca Benini,et al.  A survey of design techniques for system-level dynamic power management , 2000, IEEE Trans. Very Large Scale Integr. Syst..

[19]  Naehyuck Chang,et al.  Power saving in hand-held multimedia systems using MPEG-21 digital item adaptation , 2004, 2nd Workshop onEmbedded Systems for Real-Time Multimedia, 2004. ESTImedia 2004..

[20]  Xiliang Zhong,et al.  Energy-aware modeling and scheduling of real-time tasks for dynamic voltage scaling , 2005, 26th IEEE International Real-Time Systems Symposium (RTSS'05).

[21]  Daniel Mossé,et al.  Adaptive scheduling server for power-aware real-time tasks , 2004, TECS.

[22]  Manish Gupta,et al.  Power-Aware Microarchitecture: Design and Modeling Challenges for Next-Generation Microprocessors , 2000, IEEE Micro.

[23]  Carla Schlatter Ellis,et al.  The Synergy Between Power-Aware Memory Systems and Processor Voltage Scaling , 2003, PACS.

[24]  Mary Jane Irwin,et al.  Proceedings of the 36th annual ACM/IEEE Design Automation Conference , 1999, DAC 1999.

[25]  Tajana Rosing,et al.  Analysis of dynamic voltage scaling for system level energy management , 2008, CLUSTER 2008.

[26]  Dakai Zhu,et al.  System-Level Energy Management for Periodic Real-Time Tasks , 2006, 2006 27th IEEE International Real-Time Systems Symposium (RTSS'06).

[27]  Chaitali Chakrabarti,et al.  System-level energy-efficient dynamic task scheduling , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[28]  Jan M. Rabaey,et al.  An energy conscious methodology for early design exploration of heterogeneous DSPs , 1998, Proceedings of the IEEE 1998 Custom Integrated Circuits Conference (Cat. No.98CH36143).

[29]  Giuseppe Lipari,et al.  Minimizing CPU energy in real-time systems with discrete speed management , 2009, TECS.

[30]  Naehyuck Chang,et al.  Energy-Aware Clock-Frequency Assignment in Microprocessors and Memory Devices for Dynamic Voltage Scaling , 2007, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[31]  Kang G. Shin,et al.  Real-time dynamic voltage scaling for low-power embedded operating systems , 2001, SOSP.