By Topic

A heuristic algorithm for scheduling Out-Tree task graphs in heterogeneous computing systems

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
3 Author(s)
Jianjun Zhang ; Coll. of Sci., Naval Univ. of Eng., Wuhan, China ; Wen Kuang ; Haojie Yuan

Efficient task scheduling is critical for achieving high performance in heterogeneous computing systems. Many previous relevant works for Out-Tree task graphs focused on homogeneous environments, while neglecting the heterogeneity of processors and the economization on processors, which resulted in low practical efficiency. This paper presents a heuristic greedy algorithm based on list and task duplication for scheduling Out-Tree task graphs in heterogeneous computing systems, which tries to find the best point between balancing loads and shortening the schedule length and improves the schedule performance without increasing the time complexity of the algorithm. The comparative experimental results demonstrate that the proposed algorithm could achieve shorter schedule length while using less number of processors.

Published in:

Advanced Computational Intelligence (ICACI), 2012 IEEE Fifth International Conference on

Date of Conference:

18-20 Oct. 2012