Energy efficiency and high-performance computing
Résumé
Nowadays, high-performance computing (HPC) infrastructure can consume several megawatts. This chapter provides a state-of-the-art overview as regards energy efficiency in high-performance computing (HPC) facilities while describing the open challenges the research community has to face in the coming years to enable the building and usage of an exascale platform by 2020. It presents an overview of HPC systems. The chapter describes some research challenges and issues, while energy efficiency in clouds for HPC workload is discussed. The chapter also presents some examples of technological and economical barriers that have to be overcome before building an exascale system. The resource and job management system (RJMS) has a strategic position in the whole HPC software stack as it has a constant knowledge of both workload and resources. Virtualization is emerging as the prominent approach to mutualize the energy consumed by a single server running multiple virtual machines (VMs) instances.