Thicket
Thicket is a python-based toolkit for Exploratory Data Analysis (EDA) of parallel performance data that enables performance optimization and understanding of applications’ performance on supercomputers. It bridges the performance tool gap between being able to consider only a single instance of a simulation run (e.g., single platform, single measurement tool, or single scale) and finding actionable insights in multi-dimensional, multi-scale, multi-architecture, and multi-tool performance datasets.
You can get thicket from its GitHub repository:
$ git clone https://github.com/llnl/thicket.git
or install it using pip:
$ pip install llnl-thicket
If you are new to thicket and want to start using it, see Getting Started.
User Docs
If you encounter bugs while using thicket, you can report them by opening an issue on GitHub.
Tutorials
- Tutorial Materials
- Basic Thicket Tutorial: Thicket 101
- NOTE: An interactive version of this notebook is available in the Binder environment.
- View performance data table:
- View metadata table:
- Composing multiple Thickets:
- Filter with respect to metadata
- Group with the metadata
- View aggregated statistics table
- Filter with respect to aggregated statistics
- Calculate the median and mean of performance data column, append to aggregated statistics table
- Calculate the percentile of performance data column, append to aggregated statistics table
- View aggregated statistics call tree
- Use the Query Language
- Display histogram
- Display heatmap
- Clustering RAJA Performance Suite Dataset: Thicket Tutorial
- Thicket and Extra-P: Thicket Tutorial
- Thicket Modeling Example
- Thicket Visualization Demonstration
Developer Docs