Digital Library

cab1

 
Title:      DYNAMIC JOB SCHEDULING IN UNIFORM HYPERCUBE MULTIPROCESSORS USING A BOUNDARY VALUE BIN PACKING APPROACH FOR DETERMINISTIC MODELS
Author(s):      Srinivasan T. , Srikanth P.j.s. , Harish Subramaniam L. , Praveen K.
ISBN:      972-99353-6-X
Editors:      Nuno Guimarães and Pedro Isaías
Year:      2005
Edition:      2
Keywords:      Boundary Value Bin Packing, Deterministic Models, Dynamic Scheduling, Preemption, Mean Job Response Time, System Utilization .
Type:      Short Paper
First Page:      179
Last Page:      184
Language:      English
Cover:      cover          
Full Contents:      click to dowload Download
Paper Abstract:      In this paper, we present the problem of job scheduling in a hypercube system and propose a scheduling algorithm called Boundary Value Bin Packing for Job Scheduling (BVBP). The preemptive job scheduling algorithm proposed belongs to dynamic scheduler breed and is designed to adapt for deterministic models. The main goal of the proposed scheduling algorithm is to find an optimal schedule in which all jobs can complete their processing in the minimal deadline in a hypercube. The time complexity of this algorithm to schedule all tasks at time t is found to be O(n log n) for a n-dimensional hypercube. The performance evaluation of BVBP strategy was carried out by comparing with various other existing job scheduling disciplines in terms of system utilization, mean job response time and stability under various workloads to determine its efficiency.
   

Social Media Links

Search

Login