The HPC industry is ever facing more and more challenges on various topics and especially a significant increase in cooling requirements. To meet those requirements, liquid cooling looks like the solution. But there is an alternative cooling solution that works without a pump and without water.
Expected later in 2016, Intel will be releasing production versions of its Knights Landing (KNL) 72-core coprocessor. These next generation coprocessors are impacting the physical design of the supercomputers now coming down the pike in a number of ways. One of the most dramatic changes is the significant increase in cooling requirements – these are high wattage chips that run very hot and present some interesting engineering challenges for systems designers.
By using Direct-to-Chip liquid cooling, Mississippi State University was able to purchase more servers by minimizing the capital spent to cool the data center. The success of the initial cluster at MSU led to the installation of second cluster.
With the growth of big data, cloud and high performance computing, demands on data centers around the world are expanding every year. Unfortunately, these demands are coming up against significant opposition in the form of operating constraints, capital constraints, and sustainability goals. In this article, we look at 8 of these constraints and how direct-to-chip liquid cooling is solving them.
“Calyos is a provider of advanced 2-phase cooling solutions for electronic applications. Two platform products have been developed, one is already commercialized for power modules cooling and another one has been prototyped for electronic components cooling aimed mainly at the High Performance Computing market.”
Asetek has built a new type of liquid cooling adapter that can be fitted onto existing servers. The big win here is that the adapters cool the servers more efficiently than the air conditioning that’s typically used.