Scientific data analysis often involves complex queries across distributed datasets, requiring manipulation of multiple variables and generating derived data on the fly. Derived quantities are obtained by mathematical transformations of primary data (generated directly by applications) and allow researchers to focus in their analysis on specific aspects of their simulation. For example, in combustion simulations, calculating the magnitude of the velocity (primary data) creates a derived variable that effectively identifies areas of high interest, such as regions with intense burning. In this talk I will present optimization opportunities when the decision on when to compute the derived variables is offloaded to the I/O library and how Kokkos can be used to handled them efficiently for I/O intensive applications.

Link to the event: https://cexa-project.org/news/2025-01-15-seventh-kokkos-tea-time—copie