Lessons Learned When Building a Greenfield High Performance Computing Ecosystem
Faced with a fragmented research computing environment and growing needs for high performance computing resources, Michigan State University established the High Performance Computing Center in 2005 to serve as a central high performance computing resource for MSU's research community. Like greenfield industrial development, the center was unconstrained by existing infrastructure. The lessons learned are useful when building or maintaining an effective HPC resource and may provide insight for developing other computational services. The primary goal of a capacity HPC resource is to meet the resource's users' computational needs, rather than targeting maximum theoretical performance. The whole HPC ecosystem must be considered, including facilities, the supporting computational services, the human resources necessary to deliver these resources, and the policies to ensure optimum system utilization.