This thesis aims to explore feasible methods to profile, from the energy efficiency point of view, scientific applications by means of the performance counters and the model-specific registers provided by Intel family microprocessors. The Aurora HPC system used as testbed was made available by courtesy of CO.S.IN.T., and it belongs to the same family of machines that enabled the Eurora cluster hosted at Cineca to reach the 1st rank in the 2013 Green500. Retrieving power consumption information through NVIDIA accelerators and external monitoring and management devices on such platform is explored too.
|Titolo:||Application-level energy profiling: the CO.S.IN.T case study|
|Relatore/i esterni:||Cozzini, Stefano; Bartolini, Andrea|
|Data di pubblicazione:||18-dic-2015|
|Aree SISSA:||Laboratorio Interdisciplinare|
|Appare nelle tipologie:||8.4 Master thesis in High Performance Computing (HPC)|