Scheduling divisible loads on heterogeneousdistributed computing systems is addressed in this paper.The platform considered here is more general and realistic,where processors are connected in star topology witharbitrary communication and computation speeds and nonzerostart-up overheads. A new optimization algorithm,called WX-GA, is proposed to tackle the following fourissues: (1) How many processors are needed in computation?(2) Finding the optimal distribution sequence amongprocessors. (3) How much the load fraction should beassigned on each processor? (4) When workload is largeenough, what is the sufficient and necessary condition forthe minimum processing time? Finally, the experimentalresults indicate the efficiency and effectiveness of theproposed algorithm.
展开▼
