LAUSR

This special issue of the journal Data Science and Engineering is a result of the work fostered by the ICT COST Action IC1406 High-Performance Modelling and Simulation for Big Data Applications (cHiPSet), an EU-funded research network across 30? European countries and overseas partners (http://chipset-cost.eu/). The Big Data era poses critically difficult challenges and striking development opportunities in high-performance computing (HPC), which appears to be, in several domains, an enabling technology for the ongoing efforts to efficiently turn massively large data into valuable information and meaningful knowledge. On the other hand, modelling and simulation (MS) offer suitable abstractions to manage the complexity of analysing Big Data in the various domains. Unfortunately, modelling and simulation of big data problems does not always naturally lend itself to efficient HPC solutions. MS communities often lack the detailed expertise required to exploit the full potential of HPC solutions, and HPC architects may not be fully aware of specific MS requirements. cHiPSet is an opportunity to coordinate European research, with the support of overseas colleagues, and facilitate interactions among data-intensive MS and HPC experts, both from research and industry. This Action aims to support the development of the field, which is strategic and of long-standing interest. cHiPSet is organised around four working groups: WG1 and WG2 on HPC infrastructures and programming models for MS, while WG3 and WG4 are thematic umbrellas for data-intensive MS in Life Sciences and for Socio-economical and Physical Sciences. This DSE special issue collects contributions originating from the coordinated work of the ‘‘modelling’’ working groups WG3 and WG4 across the first two years of the Action. Andrea Bracciali and Elisabeth Larsson, guest editors of this volume and chairs of WG3 and WG4, respectively, have compiled papers presenting general examples of modelling and simulation for big data problems in the context of the two working groups. Within the Action, these and other approaches are of strong interest as paradigmatic case studies for the coordinated development of HPC solutions and for fostering collaboration across the various scientific communities in the cHiPSet network. Analogously, readers interested in state-of-the-art examples of efficient big data modelling will find the contributions of this volume of interest. This special issue is based upon work from COST Action IC1406 cHiPSet, supported by COST (European Cooperation in Science and Technology).