In situ analysis and visualization of massively parallel computations

Massively parallel simulations generate increasing volumes of big data, whose exploitation requires increasingly large storage resources, efficient networking technologies and post-processing facilities. In the coming era of exascale supercomputing, there is an emerging need for new data analysis and visualization strategies. A promising solution consists of coupling analysis with simulation, so that both are performed simultaneously. This paper describes a client–server in situ analysis for massively parallel time-evolving computations. Its application to very large turbulent transition simulations using a spectral approximation is presented. It is shown to have a low impact on the computational time with a reasonable increase of resource usage, while enriching data exploration. Computational steering is performed with real-time adjustment of the simulation parameters, thereby getting closer to a numerical experiment process. This would not have been achieved with a classical work flow using off-line visualization.