Title :
Dynamic optimization of load distribution in heterogeneous systems
Author_Institution :
Dept. of Comput. Sci., Virginia Polytech. Inst. & State Univ., Blacksburg, VA, USA
Abstract :
Considers at run-time t the dynamic load redistribution of the m(t) interacting heterogeneous unexecuted modules of a given workload over the p(t) heterogeneous processors available at time t. Average-valued parameters are used to model the workload parameters and its execution on the system processors. We seek to minimize a multi-metric objective function representing a combination of workload completion time, communication cost, resource utilization cost, and processor idle-time cost. The efficacy of a processor is defined as a composite measure of its CPU speed, memory speed, and the averaged workload parameters. The optimal load distribution is found to be the apportionment of the total load among a subset of the available processors, composed of the q(t)⩽p(t) most efficacious processors, in direct proportion to their efficacies
Keywords :
distributed processing; open systems; optimisation; resource allocation; CPU speed; available processors; average-valued parameters; communication cost; dynamic load redistribution; dynamic optimization; heterogeneous processors; interacting heterogeneous unexecuted modules; load apportioning; memory speed; multi-metric objective function minimization; optimal load distribution; processor efficacy; processor idle-time cost; resource utilization cost; workload completion time; workload parameters; Computer science; Cost function; Distributed computing; Guidelines; Parallel processing; Resource management; Runtime; Velocity measurement;
Conference_Titel :
Heterogeneous Computing Workshop, 1994., Proceedings
Conference_Location :
Cancun
Print_ISBN :
0-8186-5592-5
DOI :
10.1109/HCW.1994.324965
