Section: Application Domains

I/O intensive climate simulations for the Blue Waters post-petascale machine

A major research topic in the context of HPC simulations running on post-petascale supercomputers is to explore how to record and visualize data during the simulation efficiently without impacting the performance of the computation generating that data. Conventional practice consists in storing data on disk, moving them off-site, reading them into a workflow, and analyzing them. This approach becomes increasingly harder to use because of the large data volumes generated at fast rates, in contrast to limited back-end performance. Scalable approaches to deal with these I/O limitations are thus of utmost importance. This is one of the main challenges explicitly stated in the roadmap of the Blue Waters Project , which aims to build one of the most powerful supercomputers in the world.

In this context, the KerData project-team is exploring innovative ways to remove the limitations mentioned above through collaborative work in the framework of the Joint Inria-Illinois-ANL-BSC-JSC-RIKEN/AICS Laboratory for Extreme-Scale Computing (JLESC, formerly called JLPC), whose research activity focuses on the Blue Waters project. An example is the atmospheric simulation code CM1 (Cloud Model 1), one of the target applications of the Blue Waters machine. State-of-the-art I/O approaches, which typically consist in periodically writing a very large number of small files are inefficient: they cause bursts of I/O in the parallel file system, leading to poor performance and extreme variability (jitter). The challenge here is to investigate how to make an efficient use of the underlying file system, by avoiding synchronization and contention as much as possible. In collaboration with the JLESC, we are addressing these challenges through the Damaris approach.