A heuristic technique to improve energy efficiency with dynamic load balancing

Cabrera, Alberto; Acosta, Alejandro; Almeida, Francisco; Blanco, Vicente

doi:10.1007/s11227-018-2718-6

Cited by 7 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scheduling and load balancing are two of the most important aspects allowing to squeeze performance and optimizing the energy consumption of current parallel and distributed systems. The importance of this topic is reflected in a large number of publications and several surveys as [14][15][16][17][18].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improving utilization of heterogeneous clusters

Stafford

Bosque

2020

J Supercomput

View full text Add to dashboard Cite

Datacenters often agglutinate sets of nodes with different capabilities, leading to a sub-optimal resource utilization. One of the best ways of improving utilization is to balance the load by taking into account the heterogeneity of these clusters. This article presents a novel way of expressing computational capacity, more adequate for heterogeneous clusters, and also advocates for task migration in order to further improve the utilization. The experimental evaluation shows that both proposals are advantageous and allow improving the utilization of heterogeneous clusters and reducing the makespan to 16.7% and 17.1%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

“…An heuristic dynamic algorithm to dynamically balance the workload between different parallel processes in iterative algorithms is presented in [15]. It is based on an arbitrary objective function that can be changed, and a specific implementation to minimize energy consumption is presented.…”

Section: Related Workmentioning

confidence: 99%

Improving utilization of heterogeneous clusters

Stafford

Bosque

2020

J Supercomput

View full text Add to dashboard Cite

show abstract

“…Cabrera et al [21] propose a heuristic-based technique to improve the energy efficiency (i.e. energy consumption and the elapsed time) of heterogeneous systems with multiple different GPU accelerators by balancing the workload across various parallel processes in an iterative manner.…”

Section: Introductionmentioning

confidence: 99%

Optimization of heterogeneous systems with AI planning heuristics and machine learning: a performance and energy aware approach

Memeti

Pllana

2021

Computing

View full text Add to dashboard Cite

Heterogeneous computing systems provide high performance and energy efficiency. However, to optimally utilize such systems, solutions that distribute the work across host CPUs and accelerating devices are needed. In this paper, we present a performance and energy aware approach that combines AI planning heuristics for parameter space exploration with a machine learning model for performance and energy evaluation to determine a near-optimal system configuration. For data-parallel applications our approach determines a near-optimal host-device distribution of work, number of processing units required and the corresponding scheduling strategy. We evaluate our approach for various heterogeneous systems accelerated with GPU or the Intel Xeon Phi. The experimental results demonstrate that our approach finds a near-optimal system configuration by evaluating only about 7% of reasonable configurations. Furthermore, the performance per Joule estimation of system configurations using our machine learning model is more than 1000 $$\times $$ × faster compared to the system evaluation by program execution.

show abstract

“…In this algorithm, the task master agent and task slave agent with master-slave structure are designed in the DS, and efficient task scheduling and resource allocation are realized. Through evaluation and comparative simulation experiments, the results show that the strategy is excellent in task completion time, average response time and load balance [3][4].…”

Section: Introductionmentioning

confidence: 99%

Distributed System Application Strategy based on Dynamic Load Balancing Model of Cloud Computing

2021

DPS

View full text Add to dashboard Cite

As a new distributed computing technology, more and more applications are deployed and developed in the cloud system. At the same time, load balancing(LB) is the key technology to solve the high-performance computing in the distributed system(DS). Therefore, this paper studies the application strategy of dynamic LB model based on cloud computing(CC) in DS. CC technology and LB algorithm are briefly analyzed; The dynamic LB model based on CC is discussed, and the dynamic LB strategy is designed; Finally, the effectiveness of the application strategy of the dynamic LB model based on CC in the DS is analyzed through simulation experiments. The experimental results show that the dynamic LB algorithm designed in this paper has a good effect on the LB of each node in the DS.

show abstract

A heuristic technique to improve energy efficiency with dynamic load balancing

Cited by 7 publications

References 21 publications

Improving utilization of heterogeneous clusters

Improving utilization of heterogeneous clusters

Optimization of heterogeneous systems with AI planning heuristics and machine learning: a performance and energy aware approach

Distributed System Application Strategy based on Dynamic Load Balancing Model of Cloud Computing

Contact Info

Product

Resources

About