high performance computing on graphics processing units: hgpu.org

Machine Learning (ML) and Deep Learning (DL) are two technologies used to extract representations of the data for a specific purpose. ML algorithms take a set of data as input to generate one or several predictions. To define the final version of one model, usually there is an initial step devoted to train the algorithm (get the right final values of the parameters of the model). There are several techniques, from supervised learning to reinforcement learning, which have different requirements. On the market, there are some frameworks or APIs that reduce the effort for designing a new ML model. In this report, using the benchmark DLBENCH, we will analyse the performance and the execution modes of some well-known ML frameworks on the Finis Terrae II supercomputer when supervised learning is used. The report will show that placement of data and allocated hardware can have a large influence on the final timeto-solution.