Abstract:

Project Management in High Performance Computing (HPC) and specifically Research and Development (R&D) projects have traditionally been executed leveraging monolithic waterfall methodologies or sometimes spiral methodologies. While this has been the de-facto standard for decades with mixed results, Agile should be considered as a viable option for large-scale R&D HPC projects as well. Using the Agile methodology for projects with so many unknowns is as good an application of the methodology as the traditional application and for largely similar reasons.