High-Performance Computing (HPC) and parallel programming presents intricate challenges due to the sophisticated interplay between advanced hardware and software components. This paper delineates a case study of a cost-effective cluster comprising 24 Upboards engineered to bolster a project-based Supercomputing course. The project received the name of UpCluster, and it serves as a pragmatic, cost-efficient solution for experiential learning, mitigating the abstraction often associated with theoretical constructs. The curriculum encompasses various topics, including distributed computing, parallel computing, algorithm analysis, and the Message Passing Interface (MPI). The team meticulously documented the cluster infrastructure, providing a comprehensive guide for the configuration and utilization of the Single Board Computer cluster with Kubernetes and MPI operators. Students engaged in practical experimentation, developing scalable algorithms, and gaining valuable insights into the challenges and opportunities associated with distributed computing. These experiences fostered a deeper appreciation for the complexities and potential of distributed computing. The primary objective of this study is to demonstrate the efficacy of the cost-effective cluster in augmenting high-performance computing education. By providing a practical learning environment, the UpCluster complements theoretical instruction and empowers students to acquire practical skills in the design of large-scale distributed systems with multi-core nodes. Furthermore, the paper discusses this low-cost cluster’s potential impact and applications in HPC education. The insights from the study may benefit academic departments and institutions seeking to develop analogous project-based courses focused on high-performance computing for graduate students.
