Performance prophet: A performance modeling and prediction tool for parallel and distributed programs

High-performance computing is essential for solving large problems and for reducing the time to solution for a single problem. Current top high-performance comput-ing systems contain 1000’s of processors. Therefore, new tools are needed to support the program development that will exploit high degrees of parallelism. The issue of model-based performance evaluation of real world programs on large scale systems is addressed in this paper. We present the PerformanceProphet, which is a performance modeling and prediction tool for parallel and distributed programs. One of the main contributions of this paper is our method-ology for reducing the time needed to evaluate the model. In addition, we describe our method for automatic perfor-mance model generation. We have implemented Performan-ceProphet in Java and C++. We illustrate our approach by modeling and simulating a real-world material science par-allel program.