Moderator: Franck Cappello (Argonne National Laboratory (ANL), University of Illinois)
Panelists: Peter Lindstrom (Lawrence Livermore National Laboratory), Sheng Di (Argonne National Laboratory (ANL)), Jon Calhoun (Clemson University), Pascal Grosset (Los Alamos National Laboratory), Kartin Heitmann (Argonne National Laboratory (ANL)), Allison Baker (University Corporation for Atmospheric Research (UCAR))
Abstract: Large-scale numerical simulations, observations and experiments are generating very large datasets that are difficult to analyze, store and transfer. Data compression is an attractive and efficient technique to significantly reduce the size of scientific datasets. Lossy compression is also intriguing for potential users who need to better understand whether their applications can deal with lossy compression performance and errors. This panel will present success stories of lossy compression in simulations, instruments and AI executions. The panel will gather the developers of the most efficient lossy compressors, users of these lossy compressors and developers of tools to assess the error introduced by lossy compression. The panelists will present their inspiring success stories to the attendees, who will provide feedback on their own experience and ask questions. We expect the panel to attract interested researchers and users, novices and experts and potential users or developers of lossy compression techniques.