Easy Trace Visualizer
Context
Parallel applications can be analyze using tracing tools such as EZTrace. These tools collect events (eg. calls to MPI functions, or OpenMP constructs, etc.) during the application execution, and the resulting execution traces can be analyzed to reveal performance bugs.
As part of a collaborative research project, we develop EasyTraceAnalyzer, a generic trace analysis tool that processes various kinds of traces, and implement several performance analysis techniques (for instance, bottleneck detection).
Goal of this internship
This internship aims at designing web-based dynamic visualization tools for exploring traces. The tool could load a trace and display general information on the processes and threads (number of thread/process, duration, time spent in MPI functions, etc.), and allow users to zoom in threads in order to analyze the time spent in the different functions, etc.
The internship will consist in extracting data from a trace, by interactinf with EasyTraceAnalyzer (which is developped i C++). The data will then be processed with your prefered framework (python, matplotlib, D3js, plotly, etc.)
Keywords: HPC, MPI, performance analysis, visualization
Work conditions
- Open-source development
- Interacting with a C++ existing tool
- Development of a tool in Python/Javascript/any other language
- The internship will take place at Télécom SudParis in Evry or in Palaiseau (in the same building as Télécom Paris) – 19 place Marguerite Perey, 91120 Palaiseau
- Due to the current confinement, the internship may start remotely
