Section: Scientific Foundations

Introduction

Managing data at large scales is paramount nowadays. Governmental and commercial statistics, climate modeling, cosmology, genetics, bio-informatics, etc. are just a few examples of fields routinely generating huge amounts of data. It becomes crucial to efficiently manipulate these data, which are typically shared at a global scale. In such a context, one important goal is to provide mechanisms allowing to manage massive data blocks (e.g., of several terabytes), while providing efficient ultra-fine-grain access to literally microscopic parts of the data. Several application areas exhibit such a need for efficient scaling to huge data sizes: data mining applications  [45] , multimedia applications  [35] , database-oriented applications  [39] , [60] , [53] , etc.