Darkfiber Planning for Extensible HPC Network Design under Uncertainties

Abstract

Cabling negatively affects not only the expandability of HPC systems, but also the reliability of their communications. In effect, the deployment of a supercomputer requires thousands of kilometers of cables, which are generally buried under the floor. Hence, moving or replacing these fibers is impossible once a supercomputer is deployed. In this study, we propose to exploit an efficient cabling method to enable multiple topologies in a system expanded incrementally. This approach reduces the cost of implementing an HPC system stage after stage, while requiring a limited knowledge about the future target applications and the final size of the system.