Message from the DRBSD-8 Workshop Chairs

With an explosive growth of scientific datasets in diverse use-cases, efficient data reduction and analysis techniques are critical to the modern high performance computing (HPC) applications. For instance, an ever-growing disparity between scientific simulation execution speeds and data movement rates (such as I/O and communication) makes it increasingly infeasible for HPC applications to save all results for offline analysis. By 2024, computers are expected to compute at 1018 ops/sec but write to disk only at 1012 bytes/sec: a compute-to-output ratio 200 times worse than on the first petascale systems. In this new world, applications must increasingly perform online data analysis and reduction—tasks that introduce algorithmic, implementation, and programming model challenges that are unfamiliar to many scientists and that have major implications for the design of various elements of exascale systems.