Master of Science / Department of Computing and Information Sciences / Mitchell Neilsen / The Raspberry Pi is a versatile computer for its size and cost. The research done in this project will explore how well the Raspberry Pi performs in a clustered environment. Using the Pi as the components of a Beowulf cluster will produce an inexpensive and small cluster. The research includes constructing the cluster as well as running a computationally intensive program called OpenFOAM. The Pi cluster's performance will be measured using the High Performance Linpack benchmark. The Raspberry Pi is already used for basic computer science education and in a cluster can also be used to promote more advanced concepts such as parallel programming and high performance computing. The inexpensive cost of the cluster combined with its compact sizing would make a viable alternative for educational facilities that don't own, or can't spare, their own production clusters for educational use. This also could see use with researchers running computationally intensive programs locally on a personal cluster. The cluster produced was an eight node Pi cluster that generates up to 2.365 GFLOPS.

Commodity supercomputing clusters known as Beowulf clusters, have become a low cost alternative to traditional supercomputers. Beowulf clusters combine inexpensive computers and specialized software to achieve supercomputing power. The processing nodes in a diskless Beowulf cluster do not have a local hard disk unlike the nodes in most commodity clusters. Research has provided performance information for diskless clusters built with expensive, high performance equipment. Beowulf clusters use commodity off-the-shell hardware, and little information is available about their performance. This research includes the construction of several diskless Beowulf clusters. Using the NAS Parallel Benchmarks, the performance of these clusters was measured. Through analysis of these measurements, a descriptive performance model of diskless Beowulf clusters was produced.