Analytical modeling and simulation of the energy consumption of independent tasks

Rauber, Thomas; Rünger, Gudula

doi:10.1109/wsc.2012.6465151

Cited by 7 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed algorithms were applied to parallel application with iteration to select the best frequencies that gives the best compromising between the performance and the energy consumption. In [8], mathematical optimization model was proposed to find the optimal frequency for each node depending on its computational power. They set the slowest node to maximum frequency in the system to keep application performance degradation to minimum.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-objective Optimization of Grid Computing for Performance, Energy and Cost

Fanfakhri

Al-Sultan

Alwan

2017

KJAR

View full text Add to dashboard Cite

In this paper, new multi-objective optimization algorithm is proposed. It optimizes the execution time, the energy consumption and the cost of booked nodes in the grid architecture at the same time. The proposed algorithm selects the best frequencies depends on a new optimization function that optimized these three objectives, while giving equivalent trade-off for each one. Dynamic voltage and frequency scaling (DVFS) is used to reduce the energy consumption of the message passing parallel iterative method executed over grid. DVFS is also reduced the computing power of each processor executing the parallel applications. Therefore, the performance of these applications is decreased and so on the paid cost for the booking nodes is increased. However, the proposed multi-objective algorithm gives the minimum energy consumption and minimum cost with maximum performance at the same time. The proposed algorithm is evaluated on the SimGrid/SMPI simulator while running the parallel iterative Jacobi method. The experiments show that it reduces on average the energy consumption by up to 19.7 %, while limiting the performance and cost degradations to 3.2 % and 5.2 % respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Whereas, the frequency scaling factor not affecting the static power, refer to [6,8]. Moreover, the frequency scaling factor increases the execution time according to the equation (1).…”

Section: The Energy Consumption Modelmentioning

confidence: 99%

Multi-objective Optimization of Grid Computing for Performance, Energy and Cost

Fanfakhri

Al-Sultan

Alwan

2017

KJAR

View full text Add to dashboard Cite

show abstract

“…Many researchers [20], [21], [22], [4] divide the power consumed by a processor into two power metrics: the static and the dynamic power. While the first one is consumed as long as the computing unit is turned on, the latter is only consumed during computation times.…”

Section: B Energy Model For Heterogeneous Platformmentioning

confidence: 99%

“…The operational frequency F depends linearly on the supply voltage V , i.e., V = β · F with some constant β. This equation is used to study the change of the dynamic voltage with respect to various frequency values in [21]. The reduction process of the frequency can be expressed by the scaling factor S which is the ratio between the maximum and the new frequency as in (1).…”

Section: B Energy Model For Heterogeneous Platformmentioning

confidence: 99%

“…According to (8) the dynamic power is reduced by a factor of S −3 when reducing the frequency by a factor of S [21]. Since the FLOPS of a CPU is proportional to the frequency of a CPU, the computation time is increased proportionally to S. The new dynamic energy is the dynamic power multiplied by the new time of computation and is given by the following equation:…”

Section: B Energy Model For Heterogeneous Platformmentioning

confidence: 99%

See 1 more Smart Citation

Energy Consumption Reduction with DVFS for Message Passing Iterative Applications on Heterogeneous Architectures

Charr

Couturier

Fanfakh

et al. 2015

2015 IEEE International Parallel and Distributed Processing Symposium Workshop

View full text Add to dashboard Cite

Computing platforms are consuming more and more energy due to the increasing number of nodes composing them. To minimize the operating costs of these platforms many techniques have been used. Dynamic voltage and frequency scaling (DVFS) is one of them. It reduces the frequency of a CPU to lower its energy consumption. However, lowering the frequency of a CPU may increase the execution time of an application running on that processor. Therefore, the frequency that gives the best trade-off between the energy consumption and the performance of an application must be selected.In this paper, a new online frequency selecting algorithm for heterogeneous platforms (heterogeneous CPUs) is presented. It selects the frequencies and tries to give the best trade-off between energy saving and performance degradation, for each node computing the message passing iterative application. The algorithm has a small overhead and works without training or profiling. It uses a new energy model for message passing iterative applications running on a heterogeneous platform. The proposed algorithm is evaluated on the SimGrid simulator while running the NAS parallel benchmarks. The experiments show that it reduces the energy consumption by up to 34 % while limiting the performance degradation as much as possible. Finally, the algorithm is compared to an existing method, the comparison results show that it outperforms the latter, on average it saves 4 % more energy while keeping the same performance. IEEE International Parallel and Distributed Processing Symposium Workshops/15 $31.00

show abstract

Performance and Energy Consumption Prediction of Randomly Selected Nodes in Heterogeneous Cluster

Idrees

Fanfakh

2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Analytical modeling and simulation of the energy consumption of independent tasks

Cited by 7 publications

References 23 publications

Multi-objective Optimization of Grid Computing for Performance, Energy and Cost

Multi-objective Optimization of Grid Computing for Performance, Energy and Cost

Energy Consumption Reduction with DVFS for Message Passing Iterative Applications on Heterogeneous Architectures

Performance and Energy Consumption Prediction of Randomly Selected Nodes in Heterogeneous Cluster

Contact Info

Product

Resources

About