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

Keywords: AI  or Phylogeny  or supercomputing 

WEBINAR SERIES: AI in the life sciences: exploring possibilities, inspiring change

This record collates training materials associated with the Australian BioCommons webinar series 'AI in the life sciences: Exploring possibilities, inspiring change' that took place between June - September 2025.
Series description
Join us for a series of webinars where we explore how Artificial...

Keywords: AI, Bioinformatics, Life Sciences

WEBINAR SERIES: AI in the life sciences: exploring possibilities, inspiring change https://dresa.org.au/materials/webinar-series-ai-in-the-life-sciences-exploring-possibilities-inspiring-change This record collates training materials associated with the Australian BioCommons webinar series 'AI in the life sciences: Exploring possibilities, inspiring change' that took place between June - September 2025. Series description Join us for a series of webinars where we explore how Artificial Intelligence (AI) is shaping the future of life sciences! This series provides an accessible introduction to AI while giving direct access to experts and practical insights into real-world applications. Designed to inspire and help you recognise potential applications of AI in the life sciences, these webinars will spark new ways of thinking so that you can start applying AI in your work.  The webinars include: A foundational session covering AI basics, its evolution, and why it matters for life sciences. Watch the recording here! Guest speaker sessions where leading experts from academia and industry share how AI is being applied in different domains Live Q&A to engage with speakers, ask questions, and participate in discussions Training materials Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Series metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Campos (PDF): a PDF copy of the slides presented by Dr Túlio de Lima Campos during the webinar. Li (PDF): a PDF copy of the slides presented by Dr Maisie Li during the webinar. Salazar (PDF): a PDF copy of the slides presented by Dr Vinícius W. Salazar during the webinar. Harms (PD): a PDF copy of the slides presented by Dr Rebekah Harms during the webinar. Veit (PDF): a PDF copy of the slides presented by Dr Veit Schwämmle during the webinar. Materials shared elsewhere: Recordings of all webinars in this series are available Australian BioCommons YouTube channel. Deciphering AI for the Life Sciences  Dr Benjamin Goudey, Australian BioCommons Recording: https://www.youtube.com/watch?v=sbVzcrD-wko  Slides: https://doi.org/10.5281/zenodo.15110330 Our journey incorporating AI into our cancer computational research Dr Anna Trigos, PeterMac Recording: https://youtu.be/vCkGbWuyLaQ?si=KLtjgdMs5sQscrq- Slides: https://doi.org/10.5281/zenodo.15770502 Towards Human-AI Collaboration in Genomics and Bioinformatics Dr Maisie Li, CSIRO A Journey into Binary Classification Challenges in AI Dr Túlio de Lima Campos, Oswaldo Cruz Foundation (Brazil) and University of Melbourne Recording: https://youtu.be/3Ge9aymRKRI?si=9Rg4sl1wWXIrkKmv Deep Learning Meets the Deep Sea: AI in Microbial Oceanography  Dr Vinícius W. Salazar, Melbourne Bioinformatics AI-Driven Discovery and Therapeutic Innovation in Fungal and Bacterial Pathogenesis Dr Carlos Santos-Martin, University of Melbourne Recording: https://youtu.be/qXK7Uvf6Utk?si=15iSaeVkgnMa-nOC Improving the interpretability of AI models for cell biology and precision medicine  Dr Stefano Mangiola, University of Adelaide Bridging pharmacology and AI: Accelerating GPCR drug discovery with deep learning Dr Anh TN Nguyen, Monash University Recording: https://youtu.be/-m0tvmNgFic?si=jBruJ3U4uSnUYeoa Ensuring equity in the integration of artificial intelligence in engineering biology Dr Rebekah Harms, UNSW Data equity and the challenges of diversifying datasets for artificial intelligence Dr Yves Saint James Aquino, University of Wollongong Recording: https://youtu.be/6bPY4Dquabs?si=YLl5PxNzoEdguR0J AI-readiness of proteomics data: challenges, applications, and future perspectives Tine Claeys, UGent An overview of deep learning methods to enhance proteomics data analysis Dr Veit Schwämmle, SDU Recording: https://youtu.be/qImAEHkXBKY?si=ItX-2af6Fyhy3rY9   Melissa Burke (melissa@biocommons.org.au) AI, Bioinformatics, Life Sciences
WEBINAR SERIES: Leveraging deep learning to design custom protein-binding-proteins

This record collates training materials associated with the Australian BioCommons webinar series 'Leveraging deep learning to design custom protein-binding proteins' that took place between July - November 2025.
Series description
Deep learning methods are speeding up the process of designing...

Keywords: Structural Biology, Deep learning, Life science, AI, Bioinformatics

WEBINAR SERIES: Leveraging deep learning to design custom protein-binding-proteins https://dresa.org.au/materials/webinar-series-leveraging-deep-learning-to-design-custom-protein-binding-proteins This record collates training materials associated with the Australian BioCommons webinar series 'Leveraging deep learning to design custom protein-binding proteins' that took place between July - November 2025. Series description Deep learning methods are speeding up the process of designing proteins with desirable biophysical properties. This fast moving field leverages computational workflows that integrate deep learning models like RFdiffusion, ProteinMPNN, Bindcraft with protein structural prediction methods (Alphafold, Chai-1, Boltz-2) and traditional structural biology methods to improve protein design success rates. This webinar series features case studies from leaders in the field and is designed to inspire and help you recognise potential applications of this new approach to the design of protein-binding-proteins. Join us to hear how software such as Bindcraft is being applied to different research questions and gain hints and tips on using them in your own work. This series is brought to you by the Community for Structural Biology Computing in Australia. Training materials Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Series metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Materials shared elsewhere: Recordings of all webinars in this series are available Australian BioCommons YouTube channel. The slides from these webinars are shared in Zenodo. Using AI protein design to design binding proteins to challenging bacterial transporters Dr Rhys Grinter, University of Melbourne Recording: https://youtu.be/3Ad2gUjeSL8 Slides: https://zenodo.org/records/16511653 AIcrs: AI-Designed Anti-CRISPRs as Programmable CRISPR Inhibitors Dr Cyntia Taveneau, Monash University Recording: https://youtu.be/GSoOfyJUYSA Slides: https://zenodo.org/records/17033917 Using in silico design methods to create de novo proteins that selectively modulate apoptosis Dr Richard Birkinshaw, WEHI Recording: https://youtu.be/9-3sHy1ybpE Slides: https://zenodo.org/records/17148914 Introducing ProteinDJ: A modular and open-source framework for protein design workflows Dr Josh Hardy, WEHI Recording: https://youtu.be/xwvF62HxaF0 Slides: https://zenodo.org/uploads/17337232 Baby steps in the AI-guided design of proteins to modulate gene transcription Professor Joel Mackay, University of Sydney Recording: https://youtu.be/tKqH8WlkIX4 Slides: https://zenodo.org/records/17605782   Melissa Burke (melissa@biocommons.org.au) Structural Biology, Deep learning, Life science, AI, Bioinformatics
WEBINAR: Baby steps in the AI-guided design of proteins to modulate gene transcription

This record includes training materials associated with the Australian BioCommons webinar ‘Baby steps in the AI-guided design of proteins to modulate gene transcription’. This webinar took place on 11 November 2025 and is part of the series 'Leveraging deep learning to design custom...

Keywords: Bioinformatics, Structural biology, Protein design, AI, Deep learning

WEBINAR: Baby steps in the AI-guided design of proteins to modulate gene transcription https://dresa.org.au/materials/webinar-baby-steps-in-the-ai-guided-design-of-proteins-to-modulate-gene-transcription This record includes training materials associated with the Australian BioCommons webinar ‘Baby steps in the AI-guided design of proteins to modulate gene transcription’. This webinar took place on 11 November 2025 and is part of the series 'Leveraging deep learning to design custom protein-binding proteins'. Series description Deep learning methods are speeding up the process of designing proteins with desirable biophysical properties. This fast moving field leverages computational workflows that integrate deep learning models like RFdiffusion, ProteinMPNN, Bindcraft with protein structural prediction methods (Alphafold, Chai-1, Boltz-2) and traditional structural biology methods to improve protein design success rates. This webinar series features case studies from leaders in the field and is designed to inspire and help you recognise potential applications of this new approach to the design of protein-binding-proteins. Join us to hear how software such as Bindcraft is being applied to different research questions and gain hints and tips on using them in your own work. This series is brought to you by the Community for Structural Biology Computing in Australia. Speaker: Professor Joel Mackay, University of Sydney Host: Dr Melissa Burke, Australian BioCommons Talk title: Baby steps in the AI-guided design of proteins to modulate gene transcription Training materials Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Mackay_2025_slides (PDF): A PDF copy of the slides presented during the webinar. Materials shared elsewhere: A recording of this webinar is available on the Australian BioCommons YouTube channel: https://youtu.be/tKqH8WlkIX4 Melissa Burke (melissa@biocommons.org.au) Bioinformatics, Structural biology, Protein design, AI, Deep learning
WEBINAR: ProteinDJ: A modular and open-source framework for protein design workflows

This record includes training materials associated with the Australian BioCommons webinar ‘ProteinDJ: A modular and open-source framework for protein design workflows’. This webinar took place on 7 October 2025 and is part of the series 'Leveraging deep learning to design custom protein-binding...

Keywords: Bioinformatics, Structural Biology, Deep learning, AI, Protein design

WEBINAR: ProteinDJ: A modular and open-source framework for protein design workflows https://dresa.org.au/materials/webinar-proteindj-a-modular-and-open-source-framework-for-protein-design-workflows This record includes training materials associated with the Australian BioCommons webinar ‘ProteinDJ: A modular and open-source framework for protein design workflows’. This webinar took place on 7 October 2025 and is part of the series 'Leveraging deep learning to design custom protein-binding proteins'. Series description Deep learning methods are speeding up the process of designing proteins with desirable biophysical properties. This fast moving field leverages computational workflows that integrate deep learning models like RFdiffusion, ProteinMPNN, Bindcraft with protein structural prediction methods (Alphafold, Chai-1, Boltz-2) and traditional structural biology methods to improve protein design success rates. This webinar series features case studies from leaders in the field and is designed to inspire and help you recognise potential applications of this new approach to the design of protein-binding-proteins. Join us to hear how software such as Bindcraft is being applied to different research questions and gain hints and tips on using them in your own work. This series is brought to you by the Community for Structural Biology Computing in Australia. Speaker: Dr Josh Hardy, WEHI Host: Dr Melissa Burke, Australian BioCommons Talk title: ProteinDJ: A modular and open-source framework for protein design workflows Training materials Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Hardy_2025_slides (PDF): A PDF copy of the slides presented during the webinar. Materials shared elsewhere: A recording of this webinar is available on the Australian BIoCommons YouTube channel: https://youtu.be/xwvF62HxaF0 Related materials ProteinDJ is openly available on GitHub: https://github.com/PapenfussLab/proteindj ProteinDJ is described in the preprint: https://www.biorxiv.org/content/10.1101/2025.09.24.678028v1 Melissa Burke (melissa@biocommons.org.au) Bioinformatics, Structural Biology, Deep learning, AI, Protein design
ProteinDJ: A modular and open-source framework for protein design workflows

This record includes training materials associated with the Australian BioCommons webinar ‘ProteinDJ: A modular and open-source framework for protein design workflows’. This webinar took place on 7 October 2025 and is part of the series 'Leveraging deep learning to design custom protein-binding...

Keywords: Bioinformatics, Structural Biology, Deep learning, AI, Protein design

ProteinDJ: A modular and open-source framework for protein design workflows https://dresa.org.au/materials/proteindj-a-modular-and-open-source-framework-for-protein-design-workflows This record includes training materials associated with the Australian BioCommons webinar ‘ProteinDJ: A modular and open-source framework for protein design workflows’. This webinar took place on 7 October 2025 and is part of the series 'Leveraging deep learning to design custom protein-binding proteins'. Series description Deep learning methods are speeding up the process of designing proteins with desirable biophysical properties. This fast moving field leverages computational workflows that integrate deep learning models like RFdiffusion, ProteinMPNN, Bindcraft with protein structural prediction methods (Alphafold, Chai-1, Boltz-2) and traditional structural biology methods to improve protein design success rates. This webinar series features case studies from leaders in the field and is designed to inspire and help you recognise potential applications of this new approach to the design of protein-binding-proteins. Join us to hear how software such as Bindcraft is being applied to different research questions and gain hints and tips on using them in your own work. This series is brought to you by the Community for Structural Biology Computing in Australia. Speaker: Dr Josh Hardy, WEHI Host: Dr Melissa Burke, Australian BioCommons Talk title: ProteinDJ: A modular and open-source framework for protein design workflows Training materials Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Hardy_2025_slides (PDF): A PDF copy of the slides presented during the webinar. Materials shared elsewhere: A recording of this webinar is available on the Australian BIoCommons YouTube channel: https://youtu.be/xwvF62HxaF0 Related materials ProteinDJ is openly available on GitHub: https://github.com/PapenfussLab/proteindj ProteinDJ is described in the preprint: https://www.biorxiv.org/content/10.1101/2025.09.24.678028v1 Melissa Burke (melissa@biocommons.org.au) Bioinformatics, Structural Biology, Deep learning, AI, Protein design
WEBINAR: Detection of and phasing of hybrid accessions in a target capture dataset

This record includes training materials associated with the Australian BioCommons webinar ‘Detection of and phasing of hybrid accessions in a target capture dataset’. This webinar took place on 10 June 2021.

Hybridisation plays an important role in evolution, leading to the exchange of genes...

Keywords: Phylogenetics, Bioinformatics, Phylogeny, Genomics, Target capture sequencing

WEBINAR: Detection of and phasing of hybrid accessions in a target capture dataset https://dresa.org.au/materials/webinar-detection-of-and-phasing-of-hybrid-accessions-in-a-target-capture-dataset-51cc7740-0da1-45f1-95de-f1a47f676053 This record includes training materials associated with the Australian BioCommons webinar ‘Detection of and phasing of hybrid accessions in a target capture dataset’. This webinar took place on 10 June 2021. Hybridisation plays an important role in evolution, leading to the exchange of genes between species and, in some cases, generate new lineages. The use of molecular methods has revealed the frequency and importance of reticulation events is higher than previously thought and this insight continues with the ongoing development of phylogenomic methods that allow novel insights into the role and extent of hybridisation. Hybrids notoriously provide challenges for the reconstruction of evolutionary relationships, as they contain conflicting genetic information from their divergent parental lineages. However, this also provides the opportunity to gain insights into the origin of hybrids (including autopolyploids). This webinar explores some of the challenges and opportunities that occur when hybrids are included in a target capture sequence dataset. In particular, it describes the impact of hybrid accessions on sequence assembly and phylogenetic analysis and further explores how the information of the conflicting phylogenetic signal can be used to detect and resolve hybrid accessions. The webinar showcases a novel bioinformatic workflow, HybPhaser, that can be used to detect and phase hybrids in target capture datasets and will provide the theoretical background and concepts behind the workflow. This webinar is part of a series of webinars and workshops developed by the Genomics for Australian Plants (GAP) Initiative that focuses on the analysis of target capture sequence data. In addition to two public webinars, the GAP bioinformatics working group is offering training workshops in the use of newly developed and existing scripts in an integrated workflow to participants in the 2021 virtual Australasian Systematic Botany Society Conference. The materials are shared under a Creative Commons 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Index of training materials (PDF): List and description of all materials associated with this event including the name, format, location and a brief description of each file. Nauheimer_hybphaser_slides (PDF): Slides presented during the webinar Materials shared elsewhere: A recording of the webinar is available on the Australian BioCommons YouTube Channel: https://youtu.be/japXwTAhA5U Melissa Burke (melissa@biocommons.org.au) Phylogenetics, Bioinformatics, Phylogeny, Genomics, Target capture sequencing
WEBINAR: Conflict in multi-gene datasets: why it happens and what to do about it - deep coalescence, paralogy and reticulation

This record includes training materials associated with the Australian BioCommons webinar ‘Conflict in multi-gene datasets: why it happens and what to do about it - deep coalescence, paralogy and reticulation’. This webinar took place on 20 May 2021.

Multi-gene datasets used in phylogenetic...

Keywords: Phylogenetics, Bioinformatics, Phylogeny, Genomics, Target capture sequencing

WEBINAR: Conflict in multi-gene datasets: why it happens and what to do about it - deep coalescence, paralogy and reticulation https://dresa.org.au/materials/webinar-conflict-in-multi-gene-datasets-why-it-happens-and-what-to-do-about-it-deep-coalescence-paralogy-and-reticulation-a6743550-b904-45e1-9635-4e481ee8f739 This record includes training materials associated with the Australian BioCommons webinar ‘Conflict in multi-gene datasets: why it happens and what to do about it - deep coalescence, paralogy and reticulation’. This webinar took place on 20 May 2021. Multi-gene datasets used in phylogenetic analyses, such as those produced by the sequence capture or target enrichment used in the Genomics for Australian Plants: Australian Angiosperm Tree of Life project, often show discordance between individual gene trees and between gene and species trees. This webinar explores three different forms of discordance: deep coalescence, paralogy, and reticulation. In each case, it considers underlying biological processes, how discordance presents in the data, and what bioinformatic or phylogenetic approaches and tools are available to address these challenges. It covers Yang and Smith paralogy resolution and general information on options for phylogenetic analysis. This webinar is part of a series of webinars and workshops developed by the Genomics for Australian Plants (GAP) Initiative that focused on the analysis of target capture sequence data. In addition to two public webinars, the GAP bioinformatics working group is offering training workshops in the use of newly developed and existing scripts in an integrated workflow to participants in the 2021 virtual Australasian Systematic Botany Society Conference. The materials are shared under a Creative Commons 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Index of training materials (PDF): List and description of all materials associated with this event including the name, format, location and a brief description of each file. Schmidt-Lebuhn - paralogy lineage sorting reticulation - slides (PDF): Slides presented during the webinar   Materials shared elsewhere: A recording of the webinar is available on the Australian BioCommons YouTube Channel: https://youtu.be/1bw81q898z8 Melissa Burke (melissa@biocommons.org.au) Phylogenetics, Bioinformatics, Phylogeny, Genomics, Target capture sequencing
WEBINAR: AlphaFold: what's in it for me?

This record includes training materials associated with the Australian BioCommons webinar ‘WEBINAR: AlphaFold: what’s in it for me?’. This webinar took place on 18 April 2023.

Event description 

AlphaFold has taken the scientific world by storm with the ability to accurately predict the...

Keywords: Bioinformatics, Machine Learning, Structural Biology, Proteins, Drug discovery, AlphaFold, AI, Artificial Intelligence, Deep learning

WEBINAR: AlphaFold: what's in it for me? https://dresa.org.au/materials/webinar-alphafold-what-s-in-it-for-me-4d1ea222-4240-4b68-b9ae-7769ac664ee0 This record includes training materials associated with the Australian BioCommons webinar ‘WEBINAR: AlphaFold: what’s in it for me?’. This webinar took place on 18 April 2023. Event description  AlphaFold has taken the scientific world by storm with the ability to accurately predict the structure of any protein in minutes using artificial intelligence (AI). From drug discovery to enzymes that degrade plastics, this promises to speed up and fundamentally change the way that protein structures are used in biological research.  Beyond the hype, what does this mean for structural biology as a field (and as a career)? Dr Craig Morton, Drug Discovery Lead at the CSIRO, is an early adopter of AlphaFold and has decades of expertise in protein structure / function, protein modelling, protein – ligand interactions and computational small molecule drug discovery, with particular interest in anti-infective agents for the treatment of bacterial and viral diseases. Craig joins this webinar to share his perspective on the implications of AlphaFold for science and structural biology. He will give an overview of how AlphaFold works, ways to access AlphaFold, and some examples of how it can be used for protein structure/function analysis. Materials are shared under a Creative Commons Attribution 4.0 International agreement unless otherwise specified and were current at the time of the event. Files and materials included in this record: Event metadata (PDF): Information about the event including, description, event URL, learning objectives, prerequisites, technical requirements etc. Index of training materials (PDF): List and description of all materials associated with this event including the name, format, location and a brief description of each file. Materials shared elsewhere: A recording of this webinar is available on the Australian BioCommons YouTube Channel: https://youtu.be/4ytn2_AiH8s Melissa Burke (melissa@biocommons.org.au) Bioinformatics, Machine Learning, Structural Biology, Proteins, Drug discovery, AlphaFold, AI, Artificial Intelligence, Deep learning
Accelerating skills development in Data science and AI at scale

At the Monash Data Science and AI  platform, we believe that upskilling our research community and building a workforce with data science skills are key to accelerating the application of data science in research. To achieve this, we create and leverage new and existing training capabilities...

Keywords: AI, machine learning, eresearch skills, training, train the trainer, volunteer instructors, training partnerships, training material

Accelerating skills development in Data science and AI at scale https://dresa.org.au/materials/accelerating-skills-development-in-data-science-and-ai-at-scale-2d8a65fa-f96e-44ad-a026-cfae3f38d128 At the Monash Data Science and AI  platform, we believe that upskilling our research community and building a workforce with data science skills are key to accelerating the application of data science in research. To achieve this, we create and leverage new and existing training capabilities within and outside Monash University. In this talk, we will discuss the principles and purpose of establishing collaborative models to accelerate skills development at scale. We will talk about our approach to identifying gaps in the existing skills and training available in data science, key areas of interest as identified by the research community and various sources of training available in the marketplace. We will provide insights into the collaborations we currently have and intend to develop in the future within the university and also nationally. The talk will also cover our approach as outlined below •        Combined survey of gaps in skills and trainings for Data science and AI •        Provide seats to partners •        Share associate instructors/helpers/volunteers •        Develop combined training materials •        Publish a repository of open source trainings •        Train the trainer activities •        Establish a network of volunteers to deliver trainings at their local regions Industry plays a significant role in making some invaluable training available to the research community either through self learning platforms like AWS Machine Learning University or Instructor led courses like NVIDIA Deep Learning Institute. We will discuss how we leverage our partnerships with Industry to bring these trainings to our research community. Finally, we will discuss how we map our training to the ARDC skills roadmap and how the ARDC platforms project “Environments to accelerate Machine Learning based Discovery” has enabled collaboration between Monash University and University of Queensland to develop and deliver training together. contact@ardc.edu.au AI, machine learning, eresearch skills, training, train the trainer, volunteer instructors, training partnerships, training material
Monash University - University of Queensland training partnership in Data science and AI

We describe the peer network exchange for training that has been recently created via an ARDC funded partnership between Monash University and Universities of Queensland under the umbrella of the Queensland Cyber Infrastructure Foundation (QCIF). As part of a training program in machine learning,...

Keywords: data skills, training partnerships, data science, AI, training material

Monash University - University of Queensland training partnership in Data science and AI https://dresa.org.au/materials/monash-university-university-of-queensland-training-partnership-in-data-science-and-ai-8082bf73-d20f-4214-ad8c-95123e25a36c We describe the peer network exchange for training that has been recently created via an ARDC funded partnership between Monash University and Universities of Queensland under the umbrella of the Queensland Cyber Infrastructure Foundation (QCIF). As part of a training program in machine learning, visualisation, and computing tools, we have established a series of over 20 workshops over the year where either Monash or QCIF hosts the event for some 20-40 of their researchers and students, while some 5 places are offered to participants from the other institution. In the longer term we aim to share material developed at one institution and have trainers present it at the other. In this talk we will describe the many benefits we have found to this approach including access to a wider range of expertise in several rapidly developing fields, upskilling of trainers, faster identification of emerging training needs, and peer learning for trainers. contact@ardc.edu.au data skills, training partnerships, data science, AI, training material
HIP Advanced Workshop

Additional topics presented about HIP, covering memory management, kernel optimisation, IO optimisation and porting CUDA to HIP.

Keywords: HIP, Pawsey Supercomputing Centre, supercomputing

HIP Advanced Workshop https://dresa.org.au/materials/hip-advanced-workshop Additional topics presented about HIP, covering memory management, kernel optimisation, IO optimisation and porting CUDA to HIP. training@pawsey.org.au HIP, Pawsey Supercomputing Centre, supercomputing
PCon Preparing applications for El Capitan and beyond

As Lawrence Livermore National Laboratories (LLNL) prepares to stand up its next supercomputer, El Capitan, application teams prepare to pivot to another GPU architecture.

This talk presents how the LLNL application teams made the transition from distributed-memory, CPU-only architectures to...

Keywords: GPUs, supercomputing, HPC, PaCER

PCon Preparing applications for El Capitan and beyond https://dresa.org.au/materials/pcon-preparing-applications-for-el-capitan-and-beyond As Lawrence Livermore National Laboratories (LLNL) prepares to stand up its next supercomputer, El Capitan, application teams prepare to pivot to another GPU architecture. This talk presents how the LLNL application teams made the transition from distributed-memory, CPU-only architectures to GPUs. They share institutional best practices. They discuss new open-source software products as tools for porting and profiling applications and as avenues for collaboration across the computational science community. Join LLNL's Erik Draeger and Jane Herriman, who presented this talk at Pawsey's PaCER Conference in September 2023. training@pawsey.org.au Pawsey Supercomputing Research Centre GPUs, supercomputing, HPC, PaCER masters phd researcher ecr support professional ugrad
OpenCL

Supercomputers make use of accelerators from a variety of different hardware vendors, using devices such as multi-core CPU’s, GPU’s and even FPGA’s. OpenCL is a way for your HPC application to make effective use of heterogeneous computing devices, and to avoid code refactoring for new HPC...

Keywords: supercomputing, Pawsey Supercomputing Centre, CPUs, GPUs, OpenCL, FPGAs

Resource type: activity

OpenCL https://dresa.org.au/materials/opencl Supercomputers make use of accelerators from a variety of different hardware vendors, using devices such as multi-core CPU’s, GPU’s and even FPGA’s. OpenCL is a way for your HPC application to make effective use of heterogeneous computing devices, and to avoid code refactoring for new HPC infrastructure. training@pawsey.org.au Toby Potter supercomputing, Pawsey Supercomputing Centre, CPUs, GPUs, OpenCL, FPGAs masters ecr researcher support
AMD Profiling

The AMD profiling workshop covers the AMD suite of tools for development of HPC applications on AMD GPUs.

You will learn how to use the rocprof profiler and trace visualization tool that has long been available as part of the ROCm software suite.

You will also learn how to use the new...

Keywords: supercomputing, performance, GPUs, CPUs, AMD, HPC, ROCm

Resource type: activity

AMD Profiling https://dresa.org.au/materials/amd-profiling The AMD profiling workshop covers the AMD suite of tools for development of HPC applications on AMD GPUs. You will learn how to use the rocprof profiler and trace visualization tool that has long been available as part of the ROCm software suite. You will also learn how to use the new Omnitools - Omnitrace and Omniperf - that were introduced at the end of 2022. Omnitrace is a powerful tracing profiler for both CPU and GPU. It can collect data from a much wider range of sources and includes hardware counters and sampling approaches. Omniperf is a performance analysis tool that can help you pinpoint how your application is performing with a visual view of the memory hierarchy on the GPU as well as reporting the percentage of peak for many different measurements. training@pawsey.org.au supercomputing, performance, GPUs, CPUs, AMD, HPC, ROCm
Evaluate Application Performance using TAU and E4S

In this workshop, you learn about the Extreme-scale Scientific Software Stack and the TAU Performance System® and its interfaces to other tools and libraries. The workshop includes sample codes that illustrate the different instrumentation and measurement choices.

Topics covered include...

Keywords: supercomputing, TAU, E4S, Performance, ROCm, OpenMP

Resource type: activity

Evaluate Application Performance using TAU and E4S https://dresa.org.au/materials/evaluate-application-performance-using-tau-and-e4s In this workshop, you learn about the Extreme-scale Scientific Software Stack and the TAU Performance System® and its interfaces to other tools and libraries. The workshop includes sample codes that illustrate the different instrumentation and measurement choices. Topics covered include generating performance profiles and traces with memory utilization and headroom, I/O, and interfaces to ROCm, including ROCProfiler and ROCTracer with support for collecting hardware performance data. The workshop also covers instrumentation of OpenMP programs using OpenMP Tools Interface (OMPT), including support for target offload and measurement of a program’s memory footprint. During the session, there are hands-on activities on scalable tracing using OTF2 and visualization using the Vampir trace analysis tool. Performance data analysis using ParaProf and PerfExplorer are demonstrated using the performance data management framework (TAUdb) that includes TAU’s performance database. training@pawsey.org.au supercomputing, TAU, E4S, Performance, ROCm, OpenMP
HIP Workshop

The Heterogeneous Interface for Portability (HIP) provides a programming framework for harnessing the compute capabilities of multicore processors, such as the MI250X GPU’s on Setonix.

In this course we focus on the essentials of developing HIP applications with a focus on...

Keywords: HIP, supercomputing, Programming, GPUs, MPI, debugging

Resource type: full-course

HIP Workshop https://dresa.org.au/materials/hip-workshop The Heterogeneous Interface for Portability (HIP) provides a programming framework for harnessing the compute capabilities of multicore processors, such as the MI250X GPU’s on Setonix. In this course we focus on the essentials of developing HIP applications with a focus on supercomputing. Agenda - Introduction to HIP and high level features - How to build and run applications on Setonix with HIP and MPI - A complete line-by-line walkthrough of a HIP-enabled application - Tools and techniques for debugging and measuring the performance of HIP applications training@pawsey.org.au HIP, supercomputing, Programming, GPUs, MPI, debugging
C/C++ Refresher

The C++ programming language and its C subset is used extensively in research environments. In particular it is the language utilised in the parallel programming frameworks CUDA, HIP, and OpenCL.

This workshop is designed to equip participants with “Survival C++”, an understanding of the basic...

Keywords: supercomputing, C/C++, Programming

Resource type: activity

C/C++ Refresher https://dresa.org.au/materials/c-c-refresher The C++ programming language and its C subset is used extensively in research environments. In particular it is the language utilised in the parallel programming frameworks CUDA, HIP, and OpenCL. This workshop is designed to equip participants with “Survival C++”, an understanding of the basic syntax, how information is encoded in binary format, and how to compile and debug C++ software. training@pawsey.org.au supercomputing, C/C++, Programming
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
Merit Allocation Training for 2022

This merit allocation training session provides critical information for researchers considering to apply for time on Pawsey’s new Setonix supercomputer in 2022.

Keywords: supercomputer, supercomputing, merit allocation, allocation

Resource type: video

Merit Allocation Training for 2022 https://dresa.org.au/materials/merit-allocation-training-for-2022 This merit allocation training session provides critical information for researchers considering to apply for time on Pawsey’s new Setonix supercomputer in 2022. training@pawsey.org.au supercomputer, supercomputing, merit allocation, allocation