Slippery Rock University of Pennsylvania, United States of America
The inherent wide distribution, heterogeneity, and dynamism of today’s computational environments increasingly challenge new and existing HPC practitioners along with the cyberinfrastructure facilitators, trainers and educators who are charged with developing and delivering HPC educational content and training. Most of the computational facilities face a common challenge of supporting a diverse user base with varied skills and needs. Given the application development and computing system infrastructure comprising network, storage and servers are in a constant state of change, the continuous training and education of the computation staff is of paramount importance. The traditional classroom approach for HPC pedagogy does not fit all needs required at various levels of education. In this article we describe a sustainable model for HPC education and training that utilizes directed internship and apprenticeship approaches to train future HPC workforce. Furthermore, we also present a case study detailing how the model describes was successfully adopted and deployed at the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory (LBNL) for increasing the effectiveness of HPC education and training at all levels of education starting from high school to career workplace.