DescriptionA growing disparity between simulation speeds and I/O rates makes it increasingly infeasible for high-performance 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. Therefore, applications must increasingly perform online data analysis and reduction—tasks that introduce algorithmic and implementation challenges that are unfamiliar to many scientists and that have major implications for the design and use of exascale systems.
This trend has spurred interest in high-performance online data analysis and reduction methods, motivated by a desire to conserve I/O bandwidth, storage, and/or power; increase accuracy of data analysis results; and/or make optimal use of parallel platforms. This requires understanding the complex relationships between application design, data analysis and reduction methods, programming models, hardware, and other elements of next-generation High Performance Computers.