Supercomputers keeping people warm in the winter

Abstract

We present the design and evaluation of the heat recovery system for KTH's Lindgren, Stockholm's fastest supercomputer, a Cray XE6. Lindgren came into service in 2010 and has since been primarily used for complex numeric simulations of fluid mechanics and computational chemistry and biology. The heat exchange system collects the wasted heat from Lindgren's 36,384 CPU cores and transfers it via the standard district heating and cooling system to a neighboring building which houses the Chemistry laboratories. We analyze the impact of Lindgren's heat recycle system as a function of outside temperature and we estimate the system's carbon emission savings. Since the original installation of Lindgren in 2010, it has become common practice to use water cooling systems for supercomputers, as water is a better heat transfer medium than air. We discuss the relevant design lessons from Lindgren as they relate to practical and sustainable waste heat recovery designs for today's platforms. Finally, we estimate that the recovered heat from Lindgren reduced the carbon emissions by nearly 50 tons over the 2012-13 winter, the sample period of our analysis.