Performance prediction for complex parallel applications

Abstract

Abstract:These options often have widely varying performance charToday's massively parallel machines are typically message-passing systems consisting of hundreds or thousands of processors. Implementing parallel applications eficiently in this environment is a challenging task, and poor parallel design decisions can be expensive to correct. Tools and techniaues that allow the fast and accurate evaluation acteristics that are functions of numerous system 'and program parameters, and it can be difficult to predict a priori which options are best. Accurate prediction of the performance trade-offs of alternative strategies and of how the performance will change as program parameters change would greatly benefit program developers.of different parallelization strategies would sign@cantly improve the productivity of application developers and increase throughput on parallel architectures. This paper investigates one of the major issues in building tools to compare parallelization strategies: determiningSeveral approaches for the modeling of parallel systems have been Presented that use Markov models Or petri nets [SI, [ll], [12]. Unfortunately, it is difficult to apply these approaches to massively parallel systems or complex paralle1 applications:

Application of Recommender Systems Approaches to the MPI Program Execution Time Prediction

“…In [15] the execution time of programs on Grid systems are predicted. For time prediction purposes are used Analytical approaches [16], [17], [18], statistical approaches [19], [20], [21] approaches based on historical data [22], [23], [24], [25], time series prediction [26], [27], neural networks are also used [28], [29]. Execution time can be predicted from test runs [30].…”