Performance Analysis of Task Scheduling Heuristics in Grid

Munir, Ehsan Ullah; Li, Jianzhong; Shi, Shengfei; Rasool, Qaisar

doi:10.1109/icmlc.2007.4370679

Cited by 20 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…heuristic, Sufferage heuristic, Work queue heuristic and others [1,4,5]. Different criteria can be used for evaluating the efficiency of scheduling algorithms.…”

Section: Introductionmentioning

confidence: 99%

A New Heuristic Approach for Scheduling Independent Tasks on Heterogeneous Computing Systems

Rafsanjani¹,

Bardsiri²

2012

IJMLC

View full text Add to dashboard Cite

Abstract-Scheduling is one of the core steps to efficiently exploit the capabilities of heterogeneous computing systems. The problem of mapping meta-tasks to a machine is shown to be NP-complete. The NP-complete problem can be solved only using heuristic approach. There are a number of heuristic algorithms that were tailored to deal with scheduling of independent tasks. Different criteria can be used for evaluating the efficiency of scheduling algorithms. The most important of them are makespan, flowtime and resource utilization. In this paper, a new heuristic algorithm for scheduling meta-tasks in heterogeneous computing system is presented. The proposed algorithm improves the performance in both makespan and effective utilization of resources by reducing the idle time of the machine. The performance analyses show that the proposed algorithm has a better resource utilization rate and reduced makespan than the other known algorithms.

show abstract

“…heuristic, Sufferage heuristic, Work queue heuristic and others [1,4,5]. Different criteria can be used for evaluating the efficiency of scheduling algorithms.…”

Section: Introductionmentioning

confidence: 99%

A New Heuristic Approach for Scheduling Independent Tasks on Heterogeneous Computing Systems

Rafsanjani¹,

Bardsiri²

2012

IJMLC

View full text Add to dashboard Cite

show abstract

“…mapping of a set of tasks to a set of resources, is required to exploit the different capabilities of a set of heterogeneous resources. It is known, that an optimal mapping of computational tasks to available machines in a HC suite is an NP-complete problem [11] and as such, it is a subject to various heuristic [5,25,14] and meta-heuristic [33,42,28,7] algorithms including the differential evolution [18].…”

Section: Independent Task Schedulingmentioning

confidence: 99%

Many-Threaded Differential Evolution on the GPU

Krömer

Platoš

Snåšel

et al. 2013

Natural Computing Series

View full text Add to dashboard Cite

Differential evolution (DE) is an efficient populational meta-heuristic optimization algorithm that has been applied to many difficult real world problems. Due to the relative simplicity of its operations and real encoded data structures, it is very suitable for a parallel implementation on multicore systems and on the GPUs that nowadays reach peak performance of hundreds and thousands of giga FLOPS (floating-point operations per second). In this chapter, we present a simple yet highly parallel implementation of the differential evolution on the GPU using the CUDA architecture and demonstrate its performance on selected test problems.

show abstract

“…Efficient scheduling is required to exploit the different capabilities of a set of heterogeneous resources but it is an NP-complete problem [19] and it cannot be solved by exact methods in reasonable time. Instead, it was a subject to various heuristic [18], [20], [21] and meta -heuristic [22]- [26] algorithms. Let T = {T 1 , T 2 , .…”

Section: A Independent Task Schedulingmentioning

confidence: 99%

A comparison of many-threaded differential evolution and genetic algorithms on CUDA

Krömer

Platoš

Snášel

et al. 2011

2011 Third World Congress on Nature and Biologically Inspired Computing

View full text Add to dashboard Cite

Abstract-The recent time has seen the rise of consumer grade massively parallel environments. Powerful GPUs and multi-core processors became widely available and easy to use programming APIs such as nVidia CUDA, OpenCL, and DirectCompute simplify the development of applications that can utilize them. In this environment, the nature inspired metaheuristics can be in suitable cases implemented in parallel without additional costs. Backed by the power of modern GPGPUs, the meta-heuristics can be deployed to solve practical real world problems. In this paper, we compare differential evolution and genetic algorithms implemented on CUDA when solving the independent tasks scheduling problem.

show abstract

Performance Analysis of Task Scheduling Heuristics in Grid

Cited by 20 publications

References 11 publications

A New Heuristic Approach for Scheduling Independent Tasks on Heterogeneous Computing Systems

A New Heuristic Approach for Scheduling Independent Tasks on Heterogeneous Computing Systems

Many-Threaded Differential Evolution on the GPU

A comparison of many-threaded differential evolution and genetic algorithms on CUDA

Contact Info

Product

Resources

About