DescriptionPower and energy consumption are critical design factors for next generation large-scale HPC systems. The costs for energy are shifting budgets from investment to operating costs, and more and more often the size of systems is determined by its power needs.
As a consequence, the US Department of Energy (DOE) has set ambitious limits in terms of power consumption for their first exascale system, and many other funding agencies around the world have expressed similar goals. Yet, with today’s HPC architectures and systems, these goals are still far out of reach: they will only be achievable through a complex set of mechanisms at all levels of hardware and software, including buildings and infrastructure; all of these aspects will additionally and directly impact the application developer. On future HPC systems, running a code efficiently (as opposed to purely with high performance) will be a major requirement for every user.
In this tutorial, we will discuss the challenges caused by power and energy constraints, review available approaches in hardware and software, highlight impacts on HPC center and infrastructure design and operations, and ultimately show how this change in paradigm from “cycle awareness” to “power awareness” will impact HPC users and their work.