Automatic Cost Estimation of High-Performance Applications

In high-performance computing symbolic cost estimation is an important engineering tool that allows rapid insight in the performance effects of coding or data partitioning alternatives. In this paper we present an automatic cost estimator that compiles data parallel programs into symbolic performance models of very low solution complexity. With minimal program annotation by the user, symbolic cost models are generated in a matter of seconds, while the evaluation time of the models ranges in the milliseconds. Experimental results on three data parallel programs show that the average prediction error is less than 15 %. Apart from providing a good scalability assessment, the models correctly predict the best design alternative in all cases.