Abstract | ||
---|---|---|
Understanding power usage in parallel workloads is crucial to develop the energy-aware software that will run in future Exascale systems. In this paper, we contribute towards this goal by introducing an integrated framework to profile, monitor, model and analyze power dissipation in parallel MPI and multi-threaded scientific applications. The framework includes an own-designed device to measure internal DC power consumption and a package offering a simple interface to interact with this design as well as commercial power meters. Combined with the instrumentation package Extrae and the graphical analysis tool Paraver, the result is a useful environment to identify sources of power inefficiency directly in the source application code. For task-parallel codes, we also offer a statistical software module that inspects the execution trace of the application to calculate the parameters of an accurate model for the global energy consumption, which can be then decomposed into the average power usage per task or the nodal power dissipated per core. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICPP.2012.57 | ICPP |
Keywords | Field | DocType |
accurate model,power inefficiency,global energy consumption,power dissipation,energy-aware software,understanding power usage,internal dc power consumption,power-energy modelling,parallel scientific applications,nodal power,average power usage,commercial power meter,tracing,statistical analysis,power,high performance computing,multi threading,radiation detectors,servers,hardware,message passing,kernel | Kernel (linear algebra),Multithreading,Supercomputer,Computer science,Parallel computing,Server,Software,Energy consumption,Tracing,Message passing,Distributed computing | Conference |
Citations | PageRank | References |
40 | 1.61 | 6 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pedro Alonso | 1 | 63 | 7.19 |
Rosa M. Badia | 2 | 2234 | 160.45 |
Jesus Labarta | 3 | 1389 | 92.33 |
Maria Barreda | 4 | 72 | 7.88 |
Manuel F. Dolz | 5 | 188 | 25.29 |
Rafael Mayo | 6 | 762 | 76.75 |
Enrique S. Quintana-Orti | 7 | 405 | 32.27 |
Ruyman Reyes | 8 | 46 | 3.44 |