1. Home
  2. Materials
Register training material
11 materials found

Resource type: presentation 

Geophysical Research Data Processing and Modelling for 2030 Computation

The Cross-NCRIS National Data Assets program co-funded the ‘Geophysics 2030: Building a National High-Resolution Geophysics Reference Collection for 2030 Computation’ (Geophysics2030) project. At completion, Geophysics2030 i) trialled publishing vertically integrated geophysical datasets, making...

Keywords: Geophysics, Applied mathematics, Physical sciences, Computer and information sciences

Resource type: presentation

Geophysical Research Data Processing and Modelling for 2030 Computation https://dresa.org.au/materials/geophysical-research-data-processing-and-modelling-for-2030-computation The Cross-NCRIS National Data Assets program co-funded the ‘Geophysics 2030: Building a National High-Resolution Geophysics Reference Collection for 2030 Computation’ (Geophysics2030) project. At completion, Geophysics2030 i) trialled publishing vertically integrated geophysical datasets, making both raw datasets and successive levels of derivative data products available online in a new international self-describing data standard (first published in 2022); ii) co-located these datasets/data products with HPC computing resources required to process datasets at scale; and iii) developed new community software and environments allowing researchers to exploit the new data sets at high-resolution on a continental-scale. This ARDC, AuScope, NCI and TERN-funded project created new high-performance dataset and introduced a new, world-leading community platform that allows researchers to combine high-performance computing, high-resolution datasets, and flexible software workflows. The world-leading innovation was evidenced by new projects in collaboration with leading international researchers, including Jared Peacock, the United States Geological Survey-based leader of the new standards for Magnetotelluric (MT) data and Karl Kappler, DIAS Geophysics, who leads the development of ‘Aurora’, a National Science Foundation (USA) funded open-source software package for processing MT data using the new MTH5 standards. This Community Connect project, in partnership with NCI and AuScope, proposed to develop, deliver, and distribute a 2-day ‘Geophysical Research Data Processing and Modelling for 2030 Computation’ workshop in 2023. The training packages will consist of two parts, i) the utilisation of NCI for Geophysics processing and modelling, and ii) developing workflows for coupling Geophysical software, compute environments and datasets. Through previous engagement with the Geophysics community, we knew users of the 2030 Geophysics Collection were experts in their fields of geophysics data acquisition, processing and modelling. The community had high levels of computer literacy and deep technical skills in geophysics and research expertise. The workshop was targeted to support this advanced community and facilitate the usage of large co-located datasets and high-performance computing at the NCI HPC/cloud platform. rebecca@auscope.org.au Geophysics, Applied mathematics, Physical sciences, Computer and information sciences
Understanding your role as a Data Steward: the role of a Data Steward across the research data management lifecycle

This presentation provides an overview of the role and responsibilities of Data Steward at the University of Adelaide across the six key phases of the research data management lifecycle.

The resource was developed by the University of Adelaide Library in December 2023 as part of the...

Keywords: research data management, RDM, RDM Training, data stewardship, research data governance, role profiles

Resource type: presentation

Understanding your role as a Data Steward: the role of a Data Steward across the research data management lifecycle https://dresa.org.au/materials/understanding-your-role-as-a-data-steward-the-role-of-a-data-steward-across-the-research-data-management-lifecycle This presentation provides an overview of the role and responsibilities of Data Steward at the University of Adelaide across the six key phases of the research data management lifecycle. The resource was developed by the University of Adelaide Library in December 2023 as part of the Institutional Underpinnings program facilitated by the Australian Research Data Commons (ARDC). University of Adelaide Library contact: https://www.adelaide.edu.au/library/ask-library research data management, RDM, RDM Training, data stewardship, research data governance, role profiles mbr phd ecr researcher
Network Know-how and Data Handling Workshop

This workshop is a ‘train-the-trainer’ session that covers topics such as jargon busting, network literacy and data movement solutions. The workshop will also provide a peek at some collaborative research tools such as Jupyter Notebooks and CloudStor. You will learn about networks, integrated...

Keywords: Networks, data handling

Resource type: lesson, presentation

Network Know-how and Data Handling Workshop https://dresa.org.au/materials/network-know-how-and-data-handling-workshop This workshop is a ‘train-the-trainer’ session that covers topics such as jargon busting, network literacy and data movement solutions. The workshop will also provide a peek at some collaborative research tools such as Jupyter Notebooks and CloudStor. You will learn about networks, integrated tools, data and storage and where all these things fit in the researcher’s toolkit. This workshop is targeted at staff who would like to be more confident in giving advice to researchers about the options available to them. It is especially tailored for those with little to no technical knowledge and includes a hands-on component, using basic programming commands, but requires no previous knowledge of programming. Sara King - sara.king@aarnet.edu.au Burke, Melissa (orcid: 0000-0002-5571-8664) Networks, data handling
Porting the multi-GPU SELF-Fluids code to HIPFort

In this presentation by Dr. Joseph Schoonover of Fluid Numerics LLC, Joe shares their experience with the porting process for SELF-Fluids from multi-GPU CUDA-Fortran to multi-GPU HIPFort.

The presentation covers the design principles and roadmap for SELF and the strategy to port from...

Keywords: AMD, GPUs, supercomputer, supercomputing

Resource type: presentation

Porting the multi-GPU SELF-Fluids code to HIPFort https://dresa.org.au/materials/porting-the-multi-gpu-self-fluids-code-to-hipfort In this presentation by Dr. Joseph Schoonover of Fluid Numerics LLC, Joe shares their experience with the porting process for SELF-Fluids from multi-GPU CUDA-Fortran to multi-GPU HIPFort. The presentation covers the design principles and roadmap for SELF and the strategy to port from Nvidia-only platforms to AMD & Nvidia GPUs. Also discussed are the hurdles encountered along the way and considerations for developing multi-GPU accelerated applications in Fortran. SELF is an object-oriented Fortran library that supports the implementation of Spectral Element Methods for solving partial differential equations. SELF-Fluids is an implementation of SELF that solves the compressible Navier Stokes equations on CPU only and GPU accelerated compute platforms using the Discontinuous Galerkin Spectral Element Method. The SELF API is designed based on the assumption that SEM developers and researchers need to be able to implement derivatives in 1-D and divergence, gradient, and curl in 2-D and 3-D on scalar, vector, and tensor functions using spectral collocation, continuous Galerkin, and discontinuous Galerkin spectral element methods. The presentation discussion is placed in context of the Exascale era, where we're faced with a zoo of available compute hardware. Because of this, SELF routines provide support for GPU acceleration through AMD’s HIP and support for multi-core, multi-node, and multi-GPU platforms with MPI. training@pawsey.org.au AMD, GPUs, supercomputer, supercomputing
Embracing new solutions for in-situ visualisation

This PPT was used by Jean Favre, senior visualisation software engineer at CSCS, the Swiss National Supercomputing Centre during his presentation at P'Con '21 (Pawsey's first PaCER Conference).

This material discusses the upcoming release of ParaView v5.10, a leading scientific visualisation...

Keywords: ParaView, GPUs, supercomputer, supercomputing, visualisation, data visualisation

Resource type: presentation

Embracing new solutions for in-situ visualisation https://dresa.org.au/materials/embracing-new-solutions-for-in-situ-visualisation This PPT was used by Jean Favre, senior visualisation software engineer at CSCS, the Swiss National Supercomputing Centre during his presentation at P'Con '21 (Pawsey's first PaCER Conference). This material discusses the upcoming release of ParaView v5.10, a leading scientific visualisation application. In this release ParaView consolidates its implementation of the Catalyst API, a specification developed for simulations and scientific data producers to analyse and visualise data in situ. The material reviews some of the terminology and issues of different in-situ visualisation scenarios, then reviews early Data Adaptors for tight-coupling of simulations and visualisation solutions. This is followed by an introduction of Conduit, an intuitive model for describing hierarchical scientific data. Both ParaView-Catalyst and Ascent use Conduit’s Mesh Blueprint, a set of conventions to describe computational simulation meshes. Finally, the materials present CSCS’ early experience in adopting ParaView-Catalyst and Ascent via two concrete examples of instrumentation of some proxy numerical applications. training@pawsey.org.au ParaView, GPUs, supercomputer, supercomputing, visualisation, data visualisation
HPC file systems and what users need to consider for appropriate and efficient usage

Three videos on miscellaneous aspects of HPC usage - useful reference for new users of HPC systems.

1 – General overview of different file systems that might be available on HPC. The video goes through shared file systems such as /home and /scratch, local compute node file systems (local...

Keywords: HPC, high performance computer, File systems

Resource type: video, presentation

HPC file systems and what users need to consider for appropriate and efficient usage https://dresa.org.au/materials/hpc-file-systems-and-what-users-need-to-consider-for-appropriate-and-efficient-usage Three videos on miscellaneous aspects of HPC usage - useful reference for new users of HPC systems. 1 – General overview of different file systems that might be available on HPC. The video goes through shared file systems such as /home and /scratch, local compute node file systems (local scratch or $TMPDIR) and storage file system. It outlines what users need to consider if they wish to use any of these in their workflows. 2 – Overview of the different directories that might be present on HPC. These could include /home, /scratch, /opt, /lib and lib64, /sw and others. 3 – Overview of the Message-of-the-day file and the message that is displayed to users every time they log in. This displays info about general help and often current problems or upcoming outages. QCIF Training (training@qcif.edu.au) HPC, high performance computer, File systems
Deep Learning for Natural Language Processing

This workshop is designed to be instructor led and consists of two parts.
Part 1 consists of a lecture-demo about text processing and a hands-on session for attendees to learn how to clean a dataset.
Part 2 consists of a lecture introducing Recurrent Neural Networks and a hands-on session for...

Keywords: Deep learning, NLP, Machine learning

Resource type: presentation, tutorial

Deep Learning for Natural Language Processing https://dresa.org.au/materials/deep-learning-for-natural-language-processing This workshop is designed to be instructor led and consists of two parts. Part 1 consists of a lecture-demo about text processing and a hands-on session for attendees to learn how to clean a dataset. Part 2 consists of a lecture introducing Recurrent Neural Networks and a hands-on session for attendees to train their own RNN. The Powerpoints contain the lecture slides, while the Jupyter notebooks (.ipynb) contain the hands-on coding exercises. This workshop introduces natural language as data for deep learning. We discuss various techniques and software packages (e.g. python strings, RegEx, NLTK, Word2Vec) that help us convert, clean, and formalise text data “in the wild” for use in a deep learning model. We then explore the training and testing of a Recurrent Neural Network on the data to complete a real world task. We will be using TensorFlow v2 for this purpose. datascienceplatform@monash.edu Deep learning, NLP, Machine learning
Getting Started with Deep Learning

This lecture provides a high level overview of how you could get started with developing deep learning applications. It introduces deep learning in a nutshell and then provides advice relating to the concepts and skill sets you would need to know and have in order to build a deep learning...

Keywords: Deep learning, Machine learning

Resource type: presentation

Getting Started with Deep Learning https://dresa.org.au/materials/getting-started-with-deep-learning This lecture provides a high level overview of how you could get started with developing deep learning applications. It introduces deep learning in a nutshell and then provides advice relating to the concepts and skill sets you would need to know and have in order to build a deep learning application. The lecture also provides pointers to various resources you could use to gain a stronger foothold in deep learning. This lecture is targeted at researchers who may be complete beginners in machine learning, deep learning, or even with programming, but who would like to get into the space to build AI systems hands-on. datascienceplatform@monash.edu Deep learning, Machine learning
Visualisation and Storytelling

This workshop explores how data visualisation techniques could be utilised to better understand data and to communicate research efforts and outcomes. The workshop covers a broad range of techniques from simple and static 2D graphics to advanced 3D visualisations in order to provide a broad...

Keywords: data visualisation, storytelling

Resource type: presentation, tutorial

Visualisation and Storytelling https://dresa.org.au/materials/visualisation-and-storytelling This workshop explores how data visualisation techniques could be utilised to better understand data and to communicate research efforts and outcomes. The workshop covers a broad range of techniques from simple and static 2D graphics to advanced 3D visualisations in order to provide a broad overview of the tools available for data analysis, presentation and storytelling. We explore, among others, animated charts and graphs, web visualisation tools such as scrollytellers, and the possibilities of 3D, interactive, and even immersive visualisations. We use real world, concrete examples along the way in order to tangibly illustrate how these visualisations can be created and how viewers perceive and interact with them. We also introduce the various tools and skill sets you would need to be proficient at presenting your data to the world. By the conclusion of this workshop, you would gain familiarity with the various possibilities for presenting your own research data and outcomes. You would have a more intuitive understanding of the strengths and weaknesses of various modes of data visualisation and storytelling, and would have a starting point to obtain the right skill sets relevant to developing your visualisations of choice. datascienceplatform@monash.edu data visualisation, storytelling
Semi-Supervised Deep Learning

Modern deep neural networks require large amounts of labelled data to train. Obtaining the required labelled data is often an expensive and time consuming process. Semi-supervised deep learning involves the use of various creative techniques to train deep neural networks on partially labelled...

Keywords: Deep learning, Machine learning, semi-supervised

Resource type: presentation, tutorial

Semi-Supervised Deep Learning https://dresa.org.au/materials/semi-supervised-deep-learning Modern deep neural networks require large amounts of labelled data to train. Obtaining the required labelled data is often an expensive and time consuming process. Semi-supervised deep learning involves the use of various creative techniques to train deep neural networks on partially labelled data. If successful, it allows better training of a model despite the limited amount of labelled data available. This workshop is designed to be instructor led and covers various semi-supervised learning techniques available in the literature. The workshop consists of a lecture introducing at a high level a selection of techniques that are suitable for semi-supervised deep learning. We discuss how these techniques can be implemented and the underlying assumptions they require. The lecture is followed by a hands-on session where attendees implement a semi-supervised learning technique to train a neural network. We observe and discuss the changing performance and behaviour of the network as varying degrees of labelled and unlabelled data is provided to the network during training. datascienceplatform@monash.edu Deep learning, Machine learning, semi-supervised
Introduction to Deep Learning and TensorFlow

This workshop is intended to run as an instructor guided live event and consists of two parts. Each part consists of a lecture and a hands-on coding exercise.
Part 1 - Introduction to Deep Learning and TensorFlow
Part 2 - Introduction to Convolutional Neural Networks
The Powerpoints contain...

Keywords: Deep learning, convolutional neural network, tensorflow, Machine learning

Resource type: presentation, tutorial

Introduction to Deep Learning and TensorFlow https://dresa.org.au/materials/introduction-to-deep-learning-and-tensorflow This workshop is intended to run as an instructor guided live event and consists of two parts. Each part consists of a lecture and a hands-on coding exercise. Part 1 - Introduction to Deep Learning and TensorFlow Part 2 - Introduction to Convolutional Neural Networks The Powerpoints contain the lecture slides, while the Jupyter notebooks (.ipynb) contain the hands-on coding exercises. This workshop is an introduction to how deep learning works and how you could create a neural network using TensorFlow v2. We start by learning the basics of deep learning including what a neural network is, how information passes through the network, and how the network learns from data through the automated process of gradient descent. Workshop attendees would build, train and evaluate a neural network using a cloud GPU (Google Colab). In part 2, we look at image data and how we could train a convolution neural network to classify images. Workshop attendees will extend their knowledge from the first part to design, train and evaluate this convolutional neural network. datascienceplatform@monash.edu Deep learning, convolutional neural network, tensorflow, Machine learning