Extra-P

Latest Release

The ChangeLog for this and newer versions can be found on GitHub.

Completely rewritten in Python

New requirements:

• Matplotlib

Includes:

Command line tools

• Added the command line tool extrap-modeler to create a Extra-P experiment file with input data and models on a shell.
• Refactored extrap-print to produce a console output of an Extra-P experiment file. Removed the 95% confidence interval from the extrap-print output. Added additional options to get a list of definitions.

Multi-parameter support

• Added possibility to open set of CUBE files with multiple parameters. The number of parameters can be specified before loading the CUBE files. After a change to the number of parameters, it tries to guess the structure of the measurement directories.
• Added a model generator for multi-parameter models. Depending whether the experiment contains only one parameter or multiple parameters, the single-parameter model generators or the multi-parameter model generator can be selected for model generation.
• Several new displays for two-parameter models:
  • A display that plots selected models next to each other in distinct surface plots
  • A display that plots all selected models in the same surface plot
  • A scatter plot that shows for each parameter only the dominating function
  • The dominating model as the surface plot
  • The dominating model as a heat map
  • Contour plots
  • Interpolated contour plots
  • All selected models in the same surface plot with transparent surface and measurement points
• Added projection possibilities. Thus, when more parameters are available than the display can handle, it shows a orthogonal projection. The user can choose which parameter is shown on which axis and the value for the remaining parameters.

Minor improvements and fixes

• Fixed Opening of experiment files which contain a model generated with the refining model generator.
• Allow to pass an Extra-P experiment file to the GUI via command line argument. The file is then opened on startup of the GUI.

• Created custom GUI in python which replaces the usage of the CUBE GUI with plug-ins.
• Added command line tool to print the content of Extra-P files to the screen.
• A refactored version of the single parameter modeler from version 1.0. It requires a manual definition of the model search space.
• Added a new modeler that iteratively refined its modeling space and, thus, do not need a manual configured modeling space beforehand.
• Added a custom format to load and store perfromance models.
• Support for data input via a set of CUBE files contained in a directory. The measurement directories containing the CUBE files need to have a uniform format. The GUI tries to automatically detect the prefix name, the name of the parameter, the parameter values and the number of repetitons.
• Improved robustness against calltree variations during CUBE data import.
• Support for data input in a human readable text format.
• An experiment can contain multiple models. The user can switch between the models, create additional models or delete models.

• Refactoring of Extra-P libraries
• Created custom GUI which replace the usage of the Cube GUI for Extra-P

• First official release of Extra-P library and executable
• First official release of Extrapolation plugin for Cube 4.3+
• First official release of Modelling plugin for Cube 4.3+