The costs of HPC-based science in the exascale era

This article consists of a collection of slides from the author's conference presentation. Many science fields base their knowledge gaining process on high performance computing. Constant exponential increase in performance allows in particular natural sciences to run more and more sophisticated numerical simulations. However, one may wonder, does the quality of results correlate to the increase in costs? In particular with the advent of the Exascale era and with Big Data we are confronted with possibly prohibitive energy costs. In addition, our installations grow in size and we typically replace them every 4-6 years. The talk will analyze the cost-benefit ratio of HPC-based science and consider economic and ecological aspects. We will have a closer look onto different science fields and evaluate the impact of their research results on society.