Software power estimation and optimization for high performance, 32-bit embedded processors

Russell, Jeffry T.; Jacome, Margarida F.

doi:10.1109/iccd.1998.727070

Cited by 153 publications

(102 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further research was done on this topic by different researchers (e.g. [9], [10] and [11]). The estimation technique based on FLPA was introduced by Laurent et al [12], where the functional elements (e.g.…”

Section: Related Workmentioning

confidence: 99%

Early Energy Estimation of Networked Embedded Systems Executing Concurrent Software Components

Heinrich¹,

Bergler²,

Oswald³

2015

IJMO

View full text Add to dashboard Cite

Abstract-This paper presents and evaluates a new approach of modeling energy consumption of embedded systems resulted by concurrent software components. The objective is to enable energy estimation within early phases of system development, which allows system designers to compare different allocations of software components within networked systems.The model is presented in detail and its application demo started by a case study. Additionally, an execution time estimation for software components is presented which is necessary for the energy model -but previously not available. The model was developed being applicable early in the development process, i.e. previous to any software implementation. This was realized by using only available information.The The developed model was applied within an automotive case study which shows a theoretical energy saving potential of 36.2 %. This demonstrates the potential and relevance of modeling energy estimation within early development phases.Index Terms-Embedded systems, energy efficiency, energy estimation, networked embedded systems (automotive).

show abstract

Section: Related Workmentioning

confidence: 99%

Early Energy Estimation of Networked Embedded Systems Executing Concurrent Software Components

Heinrich¹,

Bergler²,

Oswald³

2015

IJMO

View full text Add to dashboard Cite

show abstract

“…The basic idea is the sum of the power costs of each instruction that is executed in a program can be estimated for the power cost of the program. Jeffry T. Russell [10] believes that there is actually no need to consider the individual assembly instructions to accurately predict energy and energy consumption. The energy consumption can be predicted by using the processor average power consumption multiplied by the software execution time.…”

Section: Related Workmentioning

confidence: 99%

An Energy-Aware Whole-System Dynamic Emulator – SkyEye

Cheng

Suo

Ren

et al. 2006

Emerging Directions in Embedded and Ubiquitous Computing

View full text Add to dashboard Cite

Abstract. This paper presents the design of a high performance energy-aware whole-system emulator --SkyEye. Several optimization and novel energy estimation methods used in SkyEye are proposed. By using novel searching strategy for Translated Block (TB), SkyEye save the time to find proper translated block. SkyEye uses Basic Equal Length Unit (B-ELU) method, and dynamic binary translation to reduce the simulation and energy evaluation time. The performance model of B-ELU is built to get the best length of translated block. In addition, the simulator automatically detects the voltage/frequency variation, and adjusts the energy estimation model accordingly. Using these methods, SkyEye which simulates ARM CPU based hardware system achieves marvelous performance and energy-aware statistic capability in experiments.

show abstract

“…The authors recognized that instruction clustering could be a feasible way to reduce this complexity: grouping the instructions in c clusters, the complexity is reduced to O(c y+1 ). The instruction-level power model proposed by Russel et al [8] considers the average instruction energy as invariant for all instructions in the ISA. More specifically, this model is based on the observation that, for a given class of processors, the energy per instruction shows a very small variance.…”

Section: Previous Workmentioning

confidence: 99%

Energy estimation and optimization of embedded VLIW processors based on instruction clustering

Bona¹,

Sami

Sciuto

et al. 2002

Proceedings 2002 Design Automation Conference (IEEE Cat. No.02CH37324)

View full text Add to dashboard Cite

Aim of this paper is to propose a methodology for the definition of an instruction-level energy estimation framework for VLIW (Very Long Instruction Word) processors. The power modeling methodology is the key issue to define an effective energy-aware software optimisation strategy for stateof-the-art ILP (Instruction Level Parallelism) processors. The methodology is based on an energy model for VLIW processors that exploits instruction clustering to achieve an efficient and fine grained energy estimation. The approach aims at reducing the complexity of the characterization problem for VLIW processors from exponential, with respect to the number of parallel operations in the same very long instruction, to quadratic, with respect to the number of instruction clusters. Furthermore, the paper proposes a spatial scheduling algorithm based on a low-power reordering of the parallel operations within the same long instruction. Experimental results have been carried out on the Lx processor, a 4-issue VLIW core jointly designed by HPLabs and STMicroelectronics. The results have shown an average error of 1.9% between the cluster-based estimation model and the reference design, with a standard deviation of 5.8%. For the Lx architecture, the spatial instruction scheduling algorithm provides an average energy saving of 12%.

show abstract

Software power estimation and optimization for high performance, 32-bit embedded processors

Cited by 153 publications

References 7 publications

Early Energy Estimation of Networked Embedded Systems Executing Concurrent Software Components

Early Energy Estimation of Networked Embedded Systems Executing Concurrent Software Components

An Energy-Aware Whole-System Dynamic Emulator – SkyEye

Energy estimation and optimization of embedded VLIW processors based on instruction clustering

Contact Info

Product

Resources

About