Performance Analysis of Parallel Python Applications

Python is progressively consolidating itself within the HPC community with its simple syntax, large standard library, and powerful third-party libraries for scientific computing that are especially attractive to domain scientists. Despite Python lowering the bar for accessing parallel computing, uti...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Procedia computer science Ročník 108; s. 2171 - 2179
Hlavní autori: Wagner, Michael, Llort, Germán, Mercadal, Estanislao, Giménez, Judit, Labarta, Jesús
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 2017
Predmet:
Extrae
HPC
Parallel
Paraver
Performance Analysis
Python
Tracing
Tools
HPC
Extrae
Tracing
Parallel
Performance Analysis
Python
Paraver
ISSN:1877-0509, 1877-0509
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Python is progressively consolidating itself within the HPC community with its simple syntax, large standard library, and powerful third-party libraries for scientific computing that are especially attractive to domain scientists. Despite Python lowering the bar for accessing parallel computing, utilizing the capacities of HPC systems efficiently remains a challenging task, after all. Yet, at the moment only few supporting tools exist and provide merely basic information in the form of summarized profile data. In this paper, we present our efforts in developing event-based tracing support for Python within the performance monitor Extrae to provide detailed information and enable a profound performance analysis. We present concepts to record the complete communication behavior as well as to capture entry and exit of functions in Python to provide the according application context. We evaluate our implementation in Extrae by analyzing the well-established electronic structure simulation package GPAW and demonstrate that the recorded traces provide equivalent information as for traditional C or Fortran applications and, therefore, offering the same profound analysis capabilities now for Python, as well.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2017.05.203