ABSTRACT
Dynamic voltage and frequency scaling (DVFS) offers great potential for optimizing the energy efficiency of Multiprocessor Systems-on-Chip (MPSoCs). The conventional approaches for processor voltage and frequency adjustment are not suitable for streaming multimedia applications due to the cyclic nature of dependencies in the executing tasks which can potentially violate the throughput constraints. In this paper, we propose a methodology that applies DVFS for such cyclic dependent tasks. The methodology involves an off-line analysis that assumes worst-case execution times of tasks to identify the executions that can be slowed down and an on-line analysis to utilize the slacks arising from tasks that finish their execution before the worst-case execution times. Thus, the methodology minimizes energy consumption during both off-line and on-line analysis while satisfying the throughput constraints. Experiments based on models of real-life streaming multimedia applications show that the proposed methodology reduces the overall energy consumption by 43% when compared to existing approaches.
- Marvell, StrongARM 1100 processor, 1997. http://www.marvell.com/.Google Scholar
- Intel XScale 80200 Processor, 2001. http://www.intel.com/.Google Scholar
- Transmeta, Transmeta Crusoe Processor, 2001. http://www.transmeta.com/.Google Scholar
- ARM1176 Processor, 2004. http://www.arm.com/.Google Scholar
- A. Alimonda et al. A feedback-based approach to dvfs in data-flow applications. IEEE TCAD, pages 1691--1704, 2009. Google ScholarDigital Library
- H. Aydin et al. Power-aware scheduling for periodic real-time tasks. IEEE Trans. on Comput., 53(5):584--600, may 2004. Google ScholarDigital Library
- T. D. Burd and R. W. Brodersen. Energy efficient cmos microprocessor design. In IEEE HICSS, pages 288--297, 1995. Google ScholarDigital Library
- J.-J. Chen et al. Slack reclamation for real-time task scheduling over dynamic voltage scaling multiprocessors. In IEEE SUTC, pages 358--367, 2006. Google ScholarDigital Library
- J.-J. Chen and T.-W. Kuo. Procrastination determination for periodic real-time tasks in leakage-aware dynamic voltage scaling systems. In IEEE ICCAD, pages 289--294, 2007. Google ScholarDigital Library
- P. Choudhury et al. Online dynamic voltage scaling using task graph mapping analysis for multiprocessors. In IEEE VLSID, pages 89--94, 2007. Google ScholarDigital Library
- J. Cong and K. Gururaj. Energy efficient multiprocessor task scheduling under input-dependent variation. In DATE, pages 411--416, 2009. Google ScholarDigital Library
- D. Culler et al. Parallel computer architecture: a hardware/software approach. Morgan Kaufmann Pub, 1999. Google ScholarDigital Library
- A. H. Ghamarian et al. Throughput Analysis of Synchronous Data Flow Graphs. In IEEE ACSD, pages 25--36, 2006. Google ScholarDigital Library
- F. Gruian. System-level design methods for low-energy architectures containing variable voltage processors. In Springer PACS, pages 1--12, 2001. Google ScholarDigital Library
- J. Hu and R. Marculescu. Energy-aware communication and task scheduling for network-on-chip architectures under real-time constraints. In DATE, pages 234--239, 2004. Google ScholarDigital Library
- R. Jejurikar and R. Gupta. Dynamic slack reclamation with procrastination scheduling in real-time embedded systems. In DAC, pages 111--116, 2005. Google ScholarDigital Library
- J. A. Kahle et al. Introduction to the cell multiprocessor. IBM J. Res. Dev., 49:589--604, 2005. Google ScholarDigital Library
- P. Langen and B. Juurlink. Leakage-aware multiprocessor scheduling. J. Signal Process. Syst., 57:73--88, 2009. Google ScholarDigital Library
- E. A. Lee and D. G. Messerschmitt. Static scheduling of synchronous data flow programs for digital signal processing. IEEE Trans. Comput., 36:24--35, 1987. Google ScholarDigital Library
- S. Lee et al. An intra-task dynamic voltage scaling method for soc design with hierarchical fsm and synchronous dataflow model. In ISLPED, pages 84--87, 2002. Google ScholarDigital Library
- K. Li. Performance analysis of power-aware task scheduling algorithms on multiprocessor computers with dynamic voltage and speed. IEEE TPDS, 19(11):1484--1497, nov. 2008. Google ScholarDigital Library
- J. Luo and N. K. Jha. Static and dynamic variable voltage scheduling algorithms for real-time heterogeneous distributed embedded systems. In IEEE ASP-DAC, pages 719--726, 2002. Google ScholarDigital Library
- P. Malani et al. Adaptive scheduling and voltage scaling for multiprocessor real-time applications with non-deterministic workload. In DATE, pages 652--657, 2008. Google ScholarDigital Library
- A. Nelson et al. Power minimisation for real-time dataflow applications. In IEEE DSD, pages 117--124, 2011. Google ScholarDigital Library
- D. Shin and J. Kim. Power-aware scheduling of conditional task graphs in real-time multiprocessor systems. In ISLPED, pages 408--413, 2003. Google ScholarDigital Library
- D. Shin and J. Kim. Dynamic voltage scaling of periodic and aperiodic tasks in priority-driven systems. In IEEE ASP-DAC, pages 653--658, 2004. Google ScholarDigital Library
- D. Shin and J. Kim. Optimizing intratask voltage scheduling using profile and data-flow information. IEEE TCAD, 26(2):369--385, feb. 2007. Google ScholarDigital Library
- A. K. Singh et al. A Hybrid Strategy for Mapping Multiple Throughput-constrained Applications on MPSoCs. In ACM CASES, pages 175--184, 2011. Google ScholarDigital Library
- D. C. Snowdon et al. Power management and dynamic voltage scaling: Myths and facts. In PARC, New Jersey, USA, 2005.Google Scholar
- S. Stuijk et al. SDF3: SDF For Free. In IEEE ACSD, pages 276--278, 2006. Google ScholarDigital Library
- W. Wang et al. Energy-aware dynamic slack allocation for real-time multitasking systems. Sust. Comp.: Infor. and Sys., 2:128--137, 2012.Google ScholarCross Ref
- F. Yao et al. A scheduling model for reduced cpu energy. In IEEE FOCS, pages 374--, 1995. Google ScholarDigital Library
- S. Zhang et al. Approximation algorithms for power minimization of earliest deadline first and rate monotonic schedules. In ISLPED, pages 225--230, 2007. Google ScholarDigital Library
- X. Zhong and C.-Z. Xu. System-wide energy minimization for real-time tasks: Lower bound and approximation. ACM Trans. Embed. Comput. Syst., 7:28:1--28:24, 2008. Google ScholarDigital Library
- D. Zhu et al. Scheduling with dynamic voltage/speed adjustment using slack reclamation in multiprocessor real-time systems. IEEE TPDS, 14:686--700, 2003. Google ScholarDigital Library
Index Terms
- Energy optimization by exploiting execution slacks in streaming applications on multiprocessor systems
Recommendations
Overhead-aware energy optimization for real-time streaming applications on multiprocessor System-on-Chip
In this article, we focus on solving the energy optimization problem for real-time streaming applications on multiprocessor System-on-Chip by combining task-level coarse-grained software pipelining with DVS (Dynamic Voltage Scaling) and DPM (Dynamic ...
Optimally Removing Intercore Communication Overhead for Streaming Applications on MPSoCs
This paper aims to totally remove intercore communication overhead with joint computation and communication task scheduling for streaming applications on Multiprocessor System-on-Chips (MPSoCs). Our basic idea is to let some computation and ...
An overview of achieving energy efficiency in on-chip networks
Due to the increasing bandwidth demand for the network-on-chip (NoC), interconnection networks become a dominant source of energy consumption in systems-on-chip (SoCs) and chip multi processors (CMPs). Therefore, energy efficient NoC is key to a ...
Comments