Lossy Compression for Scientific Data
TimeSunday, 14 November 20218am - 12pm CST
DescriptionLarge-scale numerical simulations, observations, experiments and AI computations are generating or consuming very large datasets that are difficult to analyze, store and transfer. Data compression is an attractive technique to significantly reduce scientific datasets. This tutorial reviews the state-of-the-art in lossy compression of scientific datasets, covers the main compression techniques (e.g., decomposition, transforms, prediction, sampling, precision reduction, etc.) and discusses in detail lossy compressors (SZ, ZFP, TThresh), compression error assessment metrics and the Z-checker tool to analyze the compression error. The tutorial addresses the following questions: why lossy compression; how does compression work; how to control compression error; and what the current use cases are. The tutorial uses examples from real-world scientific applications to illustrate the different compression techniques. From a participant perspective, the tutorial will also detail how to use compression software. This half-day tutorial is given by two of the leading teams in this domain.