Sandia's Computational Plant

Ron Brightwell
Sandia National Laboratories

The Computational Plant (Cplant) project at Sandia National Laboratories is a large-scale, massively parallel computing resource constructed from commodity computing and networking components. We have combined the benefits of commodity cluster computing with our expertise in designing, developing, using, and maintaining large-scale, massively parallel processing machines. In this poster, we present the design goals of the cluster and an approach to developing a commodity-based computational resource capable of delivering performance comparable to production-level massively parallel processing machines. We provide a description of the hardware components of our 2432-node machine, and give a detailed description of the management and runtime software components of the cluster. We also present computational performance data as well as performance measurements of functions that are critical to the management of large systems.