The KerData project-team is namely focusing on designing innovative architectures and systems for scalable data storage and processing. We initially targeted two types of infrastructures: clouds and pre-Exascale high-performance supercomputers, according to the current needs and requirements of data-intensive applications. With the recent convergence of HPC and Big Data areas, we started to investigated opportunities used by the joint use of hybrid HPC/cloud/edge infrastructures (aka the computing continuum).
Examples of such applications are:
- Cloud/edge data analytics applications (e.g., based on the MapReduce paradigm or on its extensions) handling massive data distributed at a large scale.
- Advanced (e.g., concurrency-optimized, versioning-oriented) cloud/edge services both for user-level data storage.
- Large-scale simulation applications for Exascale supercomputers.
Hybrid workflows combining simulations, dat analytics and learning running on hybrid HPC/cloud/edge infrastructures.