High-Performance Computing with TeraStat
Abstract—In the last years we are witnessing a progressive
shift toward the adoption of the cloud-computing model for
a large variety of application domains. High-performance
computing (HPC) is not an exception to this trend, with
a steadily increasing amount of performance-heavy scientific
experiments that are conducted on the cloud. However, this
approach may pose some serious security, operational and
economical issues.
In this paper we report about our experience with this
scenario, that culminated with the development of a small-scale
on-premise HPC facility called T eraStat, available through
our Department. This facility has been purposely deployed
and customized so to simplify and accelerate the execution
of performance-heavy computational experiments.
The success of T eraStat is confirmed by the large number
of experiments conducted in these years. Here, we focus on
two of the most significant case studies, outlining the positive
role played by T eraStat in their solution. The first is a large
scale analysis of climate data with annual cycles. The second is
a study about the advantages of using compression techniques
while processing large genomic data by means of a distributed
approach.