Performance prediction of parallel computation

Performance analysis of concurrent executions in parallel systems has been recognized as a challenging problem. The aim of this research is to study approximate solution techniques for this problem. We model the structure of the parallel machine and the structure of the jobs executing on such a system. We investigate rich classes of jobs, which can be expressed by sequential, And-Fork/And-Join, Or-Fork/OR-Join, and probabilistic-Fork. We propose an efficient performance prediction technique for these classes of jobs