Introduction to Linux on HPC

Click here for more detailed information 

This workshop is not taught in person but is intended to briefly cover general usage of the command line environment on HPC

Nvidia Workshop

Nvidia workshop taught by Nvidia staff.

These are usually conducted once or twice a year. The most recent was the Fall of 2023

Abstract

In this session we will cover some of the most popular and effective GPU accelerated libraries that give high performance without the requirement of writing your own custom GPU code. We will cover CUDA-X which has libraries for math, image/video processing, deep learning, and GPU tailored partner libraries. On top of CUDA-X we will cover RAPIDS which will target data science and data analytics workloads. We will conclude the session with interactive coverage of NVIDIAs profiling tools. We will conclude with a brief coverage of Python specific tools we have like CuPy and Numba for customizable GPU accelerated code. By the end of the workshop, you'll have the skills to utilize existing GPU accelerated libraries and write your own Python codes with NVIDIA GPUs!

Chapel Parallel Programming Language taught by Dr Michelle Strout

The most recent one of these was conducted Spring 2023

Chapel Tutorial for Python Programmers: Productivity and Performance in One Language

Many users of HPC systems are also Python programmers. Python is a great programming language for prototyping data analyses and simulations, but things become more challenging when trying to leverage cross-node and within-node parallelism. In this tutorial, we present the general-purpose Chapel programming language for productive, parallel programming. Participants can experiment with Chapel code examples from applications such as k-mer counting, solving a diffusion PDE, sorting, and image processing. For hands-on activities, we provide a container for quick setup and instructions on how to use Chapel on the UArizona HPC systems. Active learning exercises such as online multiple choice about converting common Python patterns into Chapel code enable participants to check what they have learned. Throughout the tutorial, existing large applications written in Chapel are highlighted with quotes from their developers and example code snippets showing Chapel usage in production.  We also give a brief introduction to Chapel's newfound support for GPU programming. Come join us for a fun couple of hours exploring how to write parallel programs in a productive and performant way!

Prerequisites: Please install podman (https://podman.io/) on your laptop beforehand or bring along a friend who has it installed on their laptop and is willing to share.  Here is how you could install and start it on a mac:

brew install podman                   // ignore the llvm15 dep error
podman machine init
podman machine start
podman machine stop                  // what you can use to stop it

Here are the commands you can use to do an initial test of chapel ahead of time if you would like:

podman pull docker.io/chapel/chapel     // takes about 3 minutes
echo 'writeln("Hello, world!");' > hello.chpl
podman run --rm -v "$PWD":/myapp -w /myapp chapel/chapel chpl -o hello hello.chpl
podman run --rm -v "$PWD":/myapp -w /myapp chapel/chapel ./hello

The Data Science Institute is a UArizona organization that provides training, support services, and connections for those in the computing/data science community:

The Data Science Institute facilitates collaboration across an increasingly diverse and active Data Science community by providing workforce development, essential technological assistance, and training to University partners. Formerly Data7, the Data Science Institute aims to foster the next generation of data-driven research by encouraging university-wide interdisciplinary collaboration, gaining external visibility, developing industry alliances, and increasing funding for research at the University of Arizona (UA).

For a list of upcoming training workshops, see: https://datascience.arizona.edu/calendar