A SIMULATION MODEL FOR THE PERFORMANCE EVALUATION OF HYBRID INTERCONNECTION ARCHITECTURES

Savita Gautam

doi:10.26483/ijarcs.v9i2.5831

Abstract

Efficient scheduling of tasks in multiprocessor interconnection networks is of primary importance for parallel execution. In this paper a new scheduling algorithm that schedules the tasks on different networks of processors is proposed and evaluated. The objective is the effective utilization of resource (processors) to execute tasks of an application. Processor networks have been used in the form of different topologies. We consider a new class of architecture known as linearly extensible multiprocessor networks which are best suited with lesser number of processors. Performance of different multiprocessor networks with the proposed algorithm as well as with other standard scheduling algorithms is evaluated in terms of performance parameters namely load balance error and execution time. Simulation results show that the linear architectures achieve better performance with the proposed scheduling scheme as compared to other considered scheduling algorithms.

Highlights

The problem of scheduling different tasks in multiprocessor systems is a well advanced research area
The tests have been run for same pattern of task structures for measuring Load Imbalance Factor (LIF) (%) and execution time
In linear type of architectures we considered Linearly Extensible Tree (LET), Linearly Extensible Triangle (LEΔ) [16] and in hybrid architectures Linearly Extensible Cube (LEC) [17] and Linear Cross Cube (LCQ) [18] with six nodes are taken into consideration

Summary

INTRODUCTION

The problem of scheduling different tasks in multiprocessor systems is a well advanced research area. In order to improve the performance of these systems further architectural innovations are being carried out to make the network simple or less complex. One such class of network is linearly extensible network which employ the desirable properties of cube-based architectures with linear extension of processors [2[, [3]. A novel approach for scheduling the tasks is presented and applied on the considered topologies This may lead us to have a better approach for efficient utilization of nodes in the networks. The results obtained from simulation model may further be utilized for detailed study of linearly extensible multiprocessor networks with different scheduling algorithms.

RELATED WORK

PROPOSED ALGORITHM

SIMULATOIN RESULTS

CONCLUSION