Automatic detection of power bottlenecks in parallel scientific applications
- First Online:
- Cite this article as:
- Barreda, M., Catalán, S., Dolz, M.F. et al. Comput Sci Res Dev (2014) 29: 221. doi:10.1007/s00450-013-0242-8
- 309 Downloads
In this paper we present an extension of the pmlib framework for power-performance analysis that permits a rapid and automatic detection of power sinks during the execution of concurrent scientific workloads. The extension is shaped in the form of a multithreaded Python module that offers high reliability and flexibility, rendering an overall inspection process that introduces low overhead. Additionally, we investigate the advantages and drawbacks of the RAPL power model, introduced in the Intel Xeon “Sandy-Bridge” CPU, versus a data acquisition system from National Instruments.