Trading off execution time for reliability in scheduling precedence-constrained tasks in heterogeneous computing

2002 ◽  
Author(s):  
A. Dogan ◽  
F. Ozguner
Keyword(s):  
Execution Time ◽  
Heterogeneous Computing

An efficient scheduling scheme using estimated execution time for heterogeneous computing systems

2013 ◽  
Vol 65 (2) ◽  
pp. 886-902 ◽  
Author(s):  
Hong Jun Choi ◽  
Dong Oh Son ◽  
Seung Gu Kang ◽  
Jong Myon Kim ◽  
Hsien-Hsin Lee ◽  
...  
Keyword(s):  
Execution Time ◽  
Heterogeneous Computing ◽  
Computing Systems ◽  
Scheduling Scheme ◽  
Heterogeneous Computing Systems

Time Optimization for Workflow Scheduling by Incorporating Level Strategy into Out-Degree

2021 ◽  
pp. 2150163
Author(s):  
Junqiang Jiang ◽  
Chenyan Zhu ◽  
Hailin Cai ◽  
Li Pan ◽  
Wenbin Li ◽  
...  
Keyword(s):  
Execution Time ◽  
High Performance ◽  
Heterogeneous Computing ◽  
Critical Role ◽  
Experimental Simulation ◽  
Workflow Scheduling ◽  
Distributed Computing Systems ◽  
Workflow Execution ◽  
Finish Time ◽  
Earliest Finish Time

Efficient workflow scheduling plays a critical role in achieving high performance in heterogeneous distributed computing systems. Given its key importance, workflow scheduling has been extensively studied, and various algorithms have been proposed in the literature mainly for systems with homogeneous or heterogeneous processors. Most of the algorithms leverage the average computation cost to prioritize tasks, and few focus on the combination of the level and out-degree of tasks, which both have a considerable impact on scheduling. A new list scheduling algorithm called level and out-degree earliest finish time (LOEFT) is proposed in this paper to address the problem of static workflow scheduling in a heterogeneous computing environment to reduce the workflow execution time. This algorithm has three major phases: task leveling, task prioritization and processor selection. In the task leveling phase, tasks are categorized into different groups based on depth value to ensure data transmission completeness. In the task prioritizing phase, the upward rank value is combined with the out-degree of every task to calculate the heterogeneous priority rank value on different processors and leverage the value to sort all tasks. In the processor selection phase, the selected task is assigned to the processor, which minimizes the former’s earliest finish time. The experimental simulation of randomly generated DAG and real-world application workflows proves that the LOEFT algorithm can significantly reduce the workflow execution time.

Prediction-Based Independent Task Scheduling for Heterogeneous Distributed Computing Systems

2012 ◽  
Vol 457-458 ◽  
pp. 1039-1046 ◽  
Author(s):  
You Wei Lu ◽  
Zhen Zhen Xu ◽  
Feng Xia
Keyword(s):  
Distributed Computing ◽  
Task Scheduling ◽  
Execution Time ◽  
Heterogeneous Computing ◽  
Scheduling Algorithm ◽  
Distributed Computing Systems ◽  
Computing Systems ◽  
Independent Task ◽  
Balance Task ◽  
Heterogeneous Computing Systems

Independent task scheduling algorithms in distributed computing systems deal with three main conflicting factors including load balance, task execution time and scheduling cost. In this paper, the problem of scheduling tasks arriving at a low rate and with long execution time in heterogeneous computing systems is studied, and a new scheduling algorithm based on prediction is proposed. This algorithm evaluates the utility of task scheduling based on statistics and prediction to solve the influence of heterogeneous computing systems. The experimental results reveal that the proposed algorithm adequately balances the conflicting factors, and thus performs better than some classical algorithms such as MCT and MET when the parameters are well selected.

scholarly journals Determining the Execution Time Distribution for a Data Parallel Program in a Heterogeneous Computing Environment

1997 ◽  
Vol 44 (1) ◽  
pp. 35-52 ◽  
Author(s):  
Yan Alexander Li ◽  
John K. Antonio ◽  
Howard Jay Siegel ◽  
Min Tan ◽  
Daniel W. Watson
Keyword(s):  
Execution Time ◽  
Time Distribution ◽  
Heterogeneous Computing ◽  
Parallel Program ◽  
Computing Environment ◽  
Data Parallel
Sign in / Sign up

Export Citation Format

Share Document