Dynamic Mapping of a Class of Independent Tasks onto Heterogeneous Computing Systems

Maheswaran, Muthucumaru; Ali, Shoukat; Siegel, Howard Jay; Hensgen, D.; Freund, Richard F.

doi:10.1006/jpdc.1999.1581

Cited by 675 publications

(501 citation statements)

References 19 publications

Supporting

Mentioning

490

Contrasting

Unclassified

Order By: Relevance

“…Each time a mapping is performed (mapping event), immediate mode heuristics only consider the new task for mapping, whereas batch mode considers a subset of tasks for mapping, thus having more information about the task mixture before mapping the tasks. As expected, the study in [25] showed that the immediate mode heuristics had shorter running times than those of the batch mode heuristics, but the batch mode heuristics gave higher performance. The heuristics proposed in this research are batch mode schemes.…”

Section: Introductionsupporting

confidence: 76%

“…There have been many previous research studies concerned with the dynamic mapping of independent tasks onto heterogeneous machines to minimize the completion time of the last finishing task (e.g., [14,18,24,25]). Our research has a different task model (with priorities and multiple deadlines) and a different performance metric (described in Section 2.2.3) that complicate the mapping problem.…”

Section: Related Workmentioning

confidence: 99%

“…Static mapping is performed when the applications are mapped in an off-line planning phase [7], e.g., planning the schedule for a set of production jobs. Dynamic mapping is performed when the applications are mapped in an on-line fashion [25], e.g., when tasks arrive at unknown intervals and are mapped as they arrive (the workload is not known a priori). In both cases, the mapping problem has been shown, in general, to be NP-complete (e.g., [10,12,18]).…”

Section: Introductionmentioning

confidence: 99%

“…Simulation is used for the evaluation and comparison of the dynamic heuristics developed in this research. As described in [25], dynamic mapping heuristics can be grouped into two categories, immediate mode and batch mode. Each time a mapping is performed (mapping event), immediate mode heuristics only consider the new task for mapping, whereas batch mode considers a subset of tasks for mapping, thus having more information about the task mixture before mapping the tasks.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamically mapping tasks with priorities and multiple deadlines in a heterogeneous environment

Kim

Shivle

Siegel

et al. 2007

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

In a distributed heterogeneous computing system, the resources have different capabilities and tasks have different requirements. To maximize the performance of the system, it is essential to assign the resources to tasks (match) and order the execution of tasks on each resource (schedule) to exploit the heterogeneity of the resources and tasks. Dynamic mapping (defined as matching and scheduling) is performed when the arrival of tasks is not known a priori. In the heterogeneous environment considered in this study, tasks arrive randomly, tasks are independent (i.e., no inter-task communication), and tasks have priorities and multiple soft deadlines. The value of a task is calculated based on the priority of the task and the completion time of the task with respect to its deadlines. The goal of a dynamic mapping heuristic in this research is to maximize the value accrued of completed tasks in a given interval of time. This research proposes, evaluates, and compares eight dynamic mapping heuristics. Two static mapping schemes (all arrival information of tasks are known) are designed also for comparison. The performance of the best heuristics is 84% of a calculated upper bound for the scenarios considered.

show abstract

Section: Introductionsupporting

confidence: 76%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamically mapping tasks with priorities and multiple deadlines in a heterogeneous environment

Kim

Shivle

Siegel

et al. 2007

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…A number of schedules have been developed and implemented in C++ by using different GA operators and encoding schemes. The Expected Time to Complete (ETC) model [23] [24] has been adopted. This assumes that we know the computing capacity of each resource, and can estimate or predict the workload information of each job and the load of prior work of each resource.…”

Section: Ga Based Resource Managementmentioning

confidence: 99%

A Survey on Application of Machine Learning to Resource Management in Grid Environment

Singh¹,

Sarkar²,

Roy³

et al. 2013

LNSE

View full text Add to dashboard Cite

Abstract-Grid represents an environment over a distributed area, incorporating heterogeneous elements such as server nodes, storage devices, and network components in a scalable, wide-area spanning compute infrastructure. Since a Grid requires large scale resource sharing, efficient resource management system (RMS) is required to manage the Quality of Service (QoS). One of the chief tasks of an RMS for Grid is selecting an appropriate and most suitable resource provider for execution of a particular job submitted by a user. This is also known as resource brokering. This paper presents a survey of resource brokering paradigms based on Machine Learning (ML). Three major ML techniques applied in Grid resource management for this purpose have been discussed.

show abstract

Robust Resource Allocation in Heterogeneous Parallel and Distributed Computing Systems

Smith

Siegel

Maciejewski

2009

Wiley Encyclopedia of Computer Science and Engineering

View full text Add to dashboard Cite

show abstract

Dynamic Mapping of a Class of Independent Tasks onto Heterogeneous Computing Systems

Cited by 675 publications

References 19 publications

Dynamically mapping tasks with priorities and multiple deadlines in a heterogeneous environment

Dynamically mapping tasks with priorities and multiple deadlines in a heterogeneous environment

A Survey on Application of Machine Learning to Resource Management in Grid Environment

Robust Resource Allocation in Heterogeneous Parallel and Distributed Computing Systems

Contact Info

Product

Resources

About