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

Matlab Training

Matlab Online Training

Matlab offers a number of free tutorials including these ones:

• Training Overview
• Machine Learning Onramp
• Deep Learning Onramp

Resources from the recent workshop:

• Slides and Exercises from today’s workshop can be downloaded at - https://tinyurl.com/DeepLearning-MATLAB-Arizona
• Free online training - Introduction to MATLAB - MATLAB Onramp
• Free in-depth MATLAB training – MATLAB Fundamentals
• Free online training - Introduction to Deep Learning – Deep Learning Onramp
• Free in-depth Deep Learning training  - Deep Learning with MATLAB
• More Resources (e-books, videos) and Examples (to help you get started with your projects)
• University of Arizona MATLAB Portal Page (Access and download MATLAB, MATLAB Online, Self-paced trainings, Technical Support and other resources)

Matlab Workshops at UArizona

Deep Learning In Matlab

October 28, 2021

Learn how you can use MATLAB to apply deep learning techniques to your work whether you’re designing algorithms, preparing and labeling data, or generating code and deploying to embedded systems.  For resources shared at the workshop see the bottom of this page.

Details

Tackling Big Data with Matlab

April 5, 2022

In this seminar you will learn strategies and techniques for handling large amounts of data in Matlab. New big data capabilities in Matlab will be highlighted including tall arrays.

Details

Singularity Training

Singularity containers let users run applications in a Linux environment of their choosing.  This is different from Docker which is not appropriate for HPC due to security concerns.  Singularity is like a container for Docker images, but is not just for Docker.  

The most important thing to know is that you create the singularity container called an image on a workstation where you have root privileges, and then transfer the image to HPC where you can execute the image. If root authority is an issue then the answer might be a virtual environmen t on your laptop, like Vagrant for MacOS

For an overview and more detailed information refer to:
Singularity Quick Start

Here are some of the use cases we support using Singularity:

• Portability and reproducibility
• You already use Docker and want to run your jobs on HPC
• You want to preserve your environment so that a system change will not affect your work
• You need newer or different libraries than are offered on HPC systems
• Someone else developed the workflow using a different version of linux
• You prefer to use something other than Red Hat / CentOS, like Ubuntu 

Introduction to OpenMP

This PDF file is a presentation from a series called Xsede * HPC Workshop.

* XSEDE, the Extreme Science and Engineering Discovery Environment, is the most advanced, powerful, and robust collection of integrated digital resources and services in the world. It is a single virtual system that scientists and researchers can use to interactively share computing resources, data, and expertise. XSEDE integrates the resources and services, makes them easier to use, and helps more people use them.