Run-time prediction of parallel applications on shared environments

Application run-time is a fundamental component in application and job scheduling. However, accurate predictions of run times are difficult to achieve for parallel applications running in shared environments where resource capacities can change dynamically over time. In this paper, we propose a run-time prediction technique for parallel applications that uses regression methods and filtering techniques to derive the application execution time without using standard performance models. The experimental results show that our use of regression models delivers tolerable prediction accuracy and that we can improve the accuracy dramatically by using appropriate filters.