JupyterHub, when properly configured and integrated with third-party code, can be used to support Jupyter Notebooks and parallel IPython clusters dispatched directly and automatically in HPC compute cluster environments. This access trivializes access to HPC resources while providing a common interface that can be deployed in any environment.
In this tutorial we will
- Introduce the concept of the Jupyter notebook - Teach visualization and data analytics using the Jupyter notebook - Demonstrate parallelization of Python code using ipyparallel and mpi4py - Demonstrate using Spark from the CU-Boulder JupyterHub implementation - Explain the implementation details of our JupyterHub HPC environment
Previous tutorials offered by Research Computing at the University of Colorado boulder are at: https://github.com/ResearchComputing/Final_Tutorials
A few example tutorials that will provide the basis for this proposal are: - Python_notebook - Python_DataAnalysis - Intro_Spark
We have also run successfully tutorials at XSEDE in 2014 and 2015.