Educational and research activitiy on High Performance Computing based Simulation and Classification Systems

Nowadays a modern approach to scientific problem solving should be based on dedicated computing systems in order to
devise   scientific   models,   simulate   phenomena,   verify   hipotesyst   that   would   be   difficult   to   recreate   in   a   physical
laboratory context. Moreover a growing number of home consumer applications are requiring a constantly increasing
amount   of   computing   resources   and   to   use   high   performance   computing   platforms.   This   activity   will   give   a   short
introduction to the mostly diffused high performance architectures and the related paradigms: MPI, OpenMP e GPGPU,
hadoop, openstack. During their apprenticeship the students will develop the basic tools to understand  and begin to
apply the  cited  paradigms  and  to used  the  connected   technologies,  with  particular  interest  about  the  modern   hybrid
programming   techniques   for   parallel   and   high   performance   computing,   as   well   as   regarding   the   most   important
paradigms used  for big data  collection and analysis,  such  as hadoop  and mapreduce,  and the related  cloud-oriented
computing infrastructures and their management. At the end of this apprenticeship the student will be able to design and
implement their own high performance system  for simulation or classification purposes.

Tutor: prof. Christian Napoli