EVEREST - dEsign enVironmEnt foR Extreme-Scale big data analytics on heterogeneous platforms
Data is collected all around us, in rapidly increasing volumes from countless sources. The question is how to extract valuable knowledge and commercial value from data. This requires novel methods, approaches and engineering paradigms in machine learning, analytics and data management. The EU-funded EVEREST project is developing a holistic approach for co-designing computation and communication in a heterogeneous, distributed, scaleable and secure system for high-performance Big Data analytics. It will simplify the programmability of heterogeneous and distributed architectures through a ‘data-driven’ design approach and by using hardware-accelerated artificial intelligence and a unified hardware/software paradigm. The project will validate its approach by applying it in real-life business scenarios such as a weather analysis-based prediction model and a smart city traffic modelling framework.