Software energy reduction techniques for variable-voltage processors

Okuma, Takanori; Yasuura, Hiroto; Ishihara, Tohru

doi:10.1109/54.914613

Cited by 32 publications

(28 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we consider that the execution time is inversely proportional to the supply voltage , an assumption commonly made in the literature [19]. Observe, however, that we make such an assumption only in order to make the illustration of our point simpler, yet the drawn conclusions are valid, in general, and do not rely on this assumption.…”

Section: A Characterization Of the Time-energy Spacementioning

confidence: 99%

“…Most of the techniques proposed in the frame of DVS, for instance, are static approaches in the sense that they can only exploit the static slack [19], [20], [29]. Nonetheless, there has been a recent interest in dynamic approaches [3], [9], [24], that is, techniques aimed at exploiting the dynamic slack, which is caused by tasks executing less number of clock cycles than their worst case.…”

Section: Introductionmentioning

confidence: 99%

“…One of the earliest papers in this area is by Yao et al [29], where the case of a single processor with continuous voltage scaling is addressed. The discrete voltage selection for minimizing energy consumption in monoprocessor systems was formulated as an integer linear programming (ILP) problem by Okuma et al [19]. DVS techniques have been applied to distributed systems [9], [12], [15], and even considering overheads caused by voltage transitions [31] and leakage energy [1].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Quasi-static assignment of voltages and optional cycles for maximizing rewards in real-time systems with energy constraints

Cortés

Eles

Peng

2005

Proceedings. 42nd Design Automation Conference, 2005.

View full text Add to dashboard Cite

Abstract-For some realtime systems, it is possible to tradeoff precision for timeliness. For such systems, typically considered under the imprecise computation model, a function assigns reward to the application depending on the amount of computation allotted to it. Also, these systems often have stringent energy constraints since many such applications run on battery powered devices. We address in this paper, the problem of maximizing rewards for imprecise computation systems that have energy constraints, more specifically, the problem of determining the voltage at which each task runs as well as the number of optional cycles such that the total reward is maximal while time and energy constraints are satisfied. We propose a quasi-static approach that is able to exploit, with low online overhead, the dynamic slack that arises from variations in the actual number of task execution cycles. In our quasi-static approach, the problem is solved in two steps: first, at design-time, a set of voltage/optional-cycles assignments are computed and stored (offline phase); second, the selection among the precomputed assignments is left for runtime, based on actual completion times and consumed energy (online phase). The advantages of the approach are demonstrated through numerous experiments with both synthetic examples and a real life application.

show abstract

Section: A Characterization Of the Time-energy Spacementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quasi-static assignment of voltages and optional cycles for maximizing rewards in real-time systems with energy constraints

Cortés

Eles

Peng

2005

Proceedings. 42nd Design Automation Conference, 2005.

View full text Add to dashboard Cite

show abstract

“…The target processor supports voltage scaling and we assume that the voltage levels can be varied in a continuous way in the interval [V min , V max ]. If only a discrete set of voltages are supported by the processor, our approach can be adapted by using well-known techniques for determining the discrete voltage levels that replace the calculated continuous one [9].…”

Section: Task and Architectural Modelsmentioning

confidence: 99%

“…Dynamic Voltage Scaling (DVS) techniques [9] are a well-known approach for reducing the energy consumption in real-time systems. By lowering the supply voltage quadratic savings in energy consumption can be achieved while performance is degraded in approximately linear fashion.…”

Section: Introductionmentioning

confidence: 99%

A Quasi-Static Approach to Minimizing Energy Consumption in Real-Time Systems under Reward Constraints

Cortés

Eles

Peng

2006

12th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'06)

View full text Add to dashboard Cite

show abstract

Reclaiming the energy of a schedule: models and algorithms

Aupy

Benoît

Dufossé

et al. 2012

Concurrency and Computation

View full text Add to dashboard Cite

We consider a task graph to be executed on a set of processors. We assume that the mapping is given, say by an ordered list of tasks to execute on each processor, and we aim at optimizing the energy consumption while enforcing a prescribed bound on the execution time. While it is not possible to change the allocation of a task, it is possible to change its speed. Rather than using a local approach such as backfilling, we consider the problem as a whole and study the impact of several speed variation models on its complexity. For continuous speeds, we give a closed-form formula for trees and series-parallel graphs, and we cast the problem into a geometric programming problem for general directed acyclic graphs. We show that the classical dynamic voltage and frequency scaling (DVFS) model with discrete modes leads to a NP-complete problem, even if the modes are regularly distributed (an important particular case in practice, which we analyze as the incremental model). On the contrary, the VDD-hopping model leads to a polynomial solution. Finally, we provide an approximation algorithm for the incremental model, which we extend for the general DVFS model.Comment: A two-page extended abstract of this work appeared as a short presentation in SPAA'2011, while the long version has been accepted for publication in "Concurrency and Computation: Practice and Experience

show abstract

Software energy reduction techniques for variable-voltage processors

Cited by 32 publications

References 15 publications

Quasi-static assignment of voltages and optional cycles for maximizing rewards in real-time systems with energy constraints

Quasi-static assignment of voltages and optional cycles for maximizing rewards in real-time systems with energy constraints

A Quasi-Static Approach to Minimizing Energy Consumption in Real-Time Systems under Reward Constraints

Reclaiming the energy of a schedule: models and algorithms

Contact Info

Product

Resources

About