Towards a novel smart and energy-aware service-oriented manager for extreme-scale applications

Exascale supercomputers will gather hundreds of million cores. The main problem to take care for running applications on such platforms is energy consumption since it is one major limitation if we consider that the currently fastest supercomputer consumes more than 12MW for a maximum performance of 10PFlops. Besides, we also need to overcome important challenges related to fault tolerance and data management in such extreme-scale systems. Thus, we need to take into consideration these challenges from an energy consumption point of view and to propose them as energy-aware services for exascale applications. At this end, we propose in this paper to provide accurate estimations of the energy consumption due to these services and offer some green and energy efficient solutions, leading to a smart and energy-aware service-oriented manager for exascale applications.