HPC-Fa14

CSE Training Workshops in HPC Tools, Fall 2014 • DCL L440


Project maintained by uiuc-cse Hosted on GitHub Pages — Theme by mattgraham

All workshops will be held in L440 Digital Computer Laboratory, an EWS computer laboratory in the basement. There is no sign-up for this series—walk-ins are welcome and encouraged!

Note the time change for the second round of workshops.

Introduction to The Linux Command Line (Bash Shell)

Oct. 17, 10:00–noon • DCL L440

This class will introduce the basic Linux environment, commands, and the elements of scripting. Scripting is a powerful way to make your data analysis consistent, reproducible, and archivable, saving you time and effort in your research.

Exercises and Notes

Please extract the data files to your desktop or home directory, and within the data directory execute the folder script. (We will do this together at the beginning of class.)

Folder script (right-click and Save As...)

Data files (right-click and Save As...)

Introduction to Scientific Computing on Illinois Campus Cluster

Oct. 24, 10:00–noon • DCL L440

This workshop will introduce the elements of scientific computing, such as numerical programming basics, navigating and working on a cluster (the Illinois Campus Cluster), and managing jobs and files effectively.

MPI for Engineers

Oct. 31, 10:00–noon • DCL L440

The Message-Passing Interface is the de facto standard for all large-scale distributed-memory cluster computing. We will examine the basics of this standard in C (and can touch on C++ and Fortran), as well as discuss some numerical coding applications and considerations. Programming experience with C is assumed.

Please right-click and Save As... the following IPython notebook to your desktop.

MPI Notebook

cd Desktop
module load canopy
ipython notebook mpi-c.ipynb

Static view of MPI notebook

OpenMP for Engineers

Nov. 7, 10:00–noon • DCL L440

OpenMP is a set of extensions to the C, C++, and Fortran languages to allow the effective control of multiple cores on shared-memory machines, such as desktop computers or single nodes of supercomputers. With a few well-placed annotations and some judicious restructuring of your current code, you can start seeing speedups from effectively using multiple processes immediately. We will discuss the basics of OpenMP and examine some applications as well. Programming experience with C or C++ is assumed.

Please right-click and Save As... the following IPython notebook to your desktop.

OpenMP Notebook

cd Desktop
module load canopy
ipython notebook omp-c.ipynb

Static view of OpenMP notebook

MATLAB Distributed

Postponed • DCL L440

About These Workshops

Contributors

Neal Davis developed these materials for Computational Science and Engineering. The command line materials also draw from Software Carpentry's excellent tutorials. This content is available under a Creative Commons Attribution 3.0 Unported License.

CC-BY-3.0

Contact

If you have any questions about course availability, concepts, or content, please contact Neal Davis, Training Coördinator for Computational Science & Engineering, at davis68 at illinois dot edu.