Distributed Neural Representation for Reactive in situ Visualization
This work enables reactive in situ visualization for scientific simulations by improving compression and caching, though it is incremental as it builds on existing implicit neural representation methods.
The paper tackles the challenge of efficiently applying implicit neural representations to distributed volume data for in situ visualization, achieving state-of-the-art compression speed, quality, and ratios while eliminating data exchanges between processes.
Implicit neural representations (INRs) have emerged as a powerful tool for compressing large-scale volume data. This opens up new possibilities for in situ visualization. However, the efficient application of INRs to distributed data remains an underexplored area. In this work, we develop a distributed volumetric neural representation and optimize it for in situ visualization. Our technique eliminates data exchanges between processes, achieving state-of-the-art compression speed, quality and ratios. Our technique also enables the implementation of an efficient strategy for caching large-scale simulation data in high temporal frequencies, further facilitating the use of reactive in situ visualization in a wider range of scientific problems. We integrate this system with the Ascent infrastructure and evaluate its performance and usability using real-world simulations.