“Exascale” refers to computing systems at least 50 times faster than the most powerful supercomputers in use today. The problem faced by Los Alamos National Laboratory (LANL) and similar labs building these systems is one of scale. To get the required performance, you need a lot of nodes, and to make it work, you need a lot of research and development.
There’s a catch-22, however: how do you write the operating systems, network stacks, launch, and boot systems for such large computers without having one on which to test it all? Use an existing supercomputer? No—the existing clusters are fully booked 24/7 doing science, they cost millions of dollars a year to run, and they may not have the architecture you need for your next-generation machine anyway. Older machines retired from science may be available, but at this scale, they cost far too much to use and are usually very hard to maintain.
The LANL solution? Build a “model supercomputer” with Raspberry Pi! Think of it as a “cluster development breadboard.”