Skip to main content

Otter post-processing tool

Project description

pyotter - The post-processing package for Otter

This is the post-processing package for use with Otter - please see the main Otter repo for details.

Getting Started

Prerequisites

The following dependencies should be installed before installing pyotter:

Installing pyotter

To install pyotter from github:

git clone https://github.com/adamtuft/pyotter.git && cd pyotter
git checkout main
pip install .

To install from PyPi:

pip install pyotter

Using pyotter

A trace recorded by Otter can be converted into a graph in graph.dot with:

python3 -m otter my-otter-trace/my-otter-trace.otf2 -o graph.dot

The graph, saved to graph.dot, can then be visualised using the dot command line tool included with Graphviz or a graph visualisation tool such as yEd-Desktop or yEd-Live.

Future Work

The future direction of development may include, in no particular order:

  • <input type="checkbox" disabled="" /> Visualise actual work done per task.
  • <input type="checkbox" disabled="" /> Automatic detection of the critical path.
  • <input type="checkbox" disabled="" /> Support for MPI+OpenMP applications.
  • <input type="checkbox" disabled="" /> Support for GPU-offloaded tasks.
  • <input type="checkbox" disabled="" /> Stronger graph visualisation capabilities.

Contributing

Contributions are welcome! If you would like to contribute, please fork the repository and use the contributions branch. There is no specific style guide, although I would be grateful if you could code in a style consistent with that of the main project.

Issues, Questions and Feature Requests

Please post any of the above in the main Otter repo so as to keep everything in one place.

Licensing

pyotter is released under the BSD 3-clause license. See LICENSE for details.

Copyright (c) 2021, Adam Tuft All rights reserved.

Acknowledgements

pyotter was conceived and developed as the subject of a final project and dissertation for the the Scientific Computing and Data Analysis MSc (MISCADA) at Durham University, UK. The author is grateful for the guidance and support of his supervisor Prof. Tobias Weinzierl and for the invaluable assistance provided by Dr. Holger Schulz.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pyotter, version 0.1.1
Filename, size File type Python version Upload date Hashes
Filename, size pyotter-0.1.1-py3-none-any.whl (13.4 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size pyotter-0.1.1.tar.gz (13.0 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page