Estimation of the Speedup of Distributed Applications

Abstract

Speedup is one of the main performance charac- teristics of distributed applications. It is defined as the ratio of application’s execution time on a single processor to the execution time, of the same workload, on a system composed on N processors. This paper analyzes, in very general terms, the speedup that can be achieved in distributed environ- ments and shows why some applications scale very well with the number of processors while others have strict limitations on the speedup that can be achieved in distributed environ- ments. The existence of such limitations simply means that a straightforward distribution of a (sequential) workload is not a satisfactory approach, and new algorithms are needed to use distributed environments in a more satisfactory way.