Knowledge Base Resources

It's not uncommon to see beautiful visualizations in HPC center galleries, but the majority of these are either rendered off the HPC or created using programs that run on OpenGL or custom rasterization techniques. To put it simply the next generation of graphics provided by OpenGL's successor Vulkan is strangely absent in the super computing world. The aim of this survey of available resources is to determine the systems that can support Vulkan workflows and programs. This will assist users in getting past some of the first hurdles in using Vulkan in HPC contexts.

A VPN, or Virtual Private Network, is a technology that creates a secure tunnel between your device and a VPN server. This tunnel encrypts all of your traffic, making it unreadable to anyone who tries to intercept it.

This tutorial series and documentation covers topics on using Python on HPC clusters. The specific steps are based on the HOPPER cluster at George Mason University in Fairfax, VA. They should be implementable on most HPC clusters that have the SLURM scheduler installed, the Environment Modules system for managing packages and Open onDemand for a web-based GUI to access the cluster resources.

Jetstream2 makes cutting-edge high-performance computing and software easy to use for your research regardless of your project’s scale—even if you have limited experience with supercomputing systems.Cloud-based and on-demand, the 24/7 system includes discipline-specific apps. You can even create virtual machines that look and feel like your lab workstation or home machine, with thousands of times the computing power.

Running QGIS tools from the command line

This tutorial is essentially the "hello world" of image recognition and feed-forward neural network (using PyTorch). Using the MNIST database (filled within images of handwritten digits), the tutorial will instruct how to build a feed-forward neural network that can recognize handwritten digits. A solid understanding of feed-forward and back-propagation is recommended.

pip stands for "pip installs packages". It's the go-to package manager for Python, allowing developers to install, update, and manage software libraries and dependencies used in Python projects. With just a few commands in your terminal or command prompt, pip makes it effortless to fetch libraries from the Python Package Index (PyPI) and integrate them into your projects. This guide will walk you through the basics of pip, from installation to advanced package management.

Landing Page for Bridges-2 information

Plots.jl is the most widely used plotting library for the Julia programming language. It's known for being especially powerful in its versatility and intuitiveness. It's limited set of dependencies and wide applicability across different graphics packages make it especially helpful in visualizing the results of your latest Julia implementation. However, there are still multiple options available for Julia programmers to visualize their datasets. The second link details a comparison against a variety of Julia packages.

A series of interviews with women in the HPC community

CMake is an open-source tool used to manage the build process in operating systems. This tutorial takes you through how to use CMake from the very basics with example projects.

phenoACCESS-24: Workshop on Research Computing and Plant Phenotyping High-throughput plant phenotyping is computationally intensive, requiring data storage, data processing and analysis, research computing expertise, and mechanisms for data sharing. This workshop is aimed at research computing workforce development by addressing questions such as what is plant phenotyping; what types of data are collected; what are the preprocessing and analytical needs; what tools and platforms exist for data capture, management, analysis, and storage; and how best to collaborate and engage with phenotyping researchers. The full-day agenda will include speakers (scientists and research compute staff); panel discussions (how to work with research computing staff and facilities; how to engage with phenotyping scientists), and networking opportunities (meet-and-greet, ice breakers, small group discussions). The videos and slide decks for the talks are included on the linked page.

This article discusses the importance of fairness in machine learning and provides insights into how Google approaches fairness in their ML models. The article covers several key topics: Introduction to fairness in ML: It provides an overview of why fairness is essential in machine learning systems, the potential biases that can arise, and the impact of biased models on different communities. Defining fairness: The article discusses various definitions of fairness, including individual fairness, group fairness, and disparate impact. It explains the challenges in achieving fairness due to trade-offs and the need for thoughtful considerations. Addressing bias in training data: It explores how biases can be present in training data and offers strategies to identify and mitigate these biases. Techniques like data preprocessing, data augmentation, and synthetic data generation are discussed. Fairness in ML algorithms: The article examines the potential biases that can arise from different machine learning algorithms, such as classification and recommendation systems. It highlights the importance of evaluating and monitoring models for fairness throughout their lifecycle. Fairness tools and resources: It showcases various tools and resources available to practitioners and developers to help measure, understand, and mitigate bias in machine learning models. Google's TensorFlow Extended (TFX) and What-If Tool are mentioned as examples. Google's approach to fairness: The article highlights Google's commitment to fairness and the steps they take to address fairness challenges in their ML models. It mentions the use of fairness indicators, ongoing research, and partnerships to advance fairness in AI. Overall, the article provides a comprehensive overview of fairness in machine learning and offers insights into Google's approach to building fair ML models.

There is a detailed explanation about communication routines and managing methods of different MPI libraries, as well as several exercises designed for users to get familiar with the implementation of MPI build process.

Docker allows for containerization of any task - basically a smaller, scalable version of a virtual machine. This is very useful when transferring work across computing environments, as it ensures reproducibility.

This presentation gives a detailed breakdown of the outcome of my master's thesis which was focused on making HPC Clusters accessible across all disciplines in a university setting "Our Case Study was the university of Cincinnati".

The Neuroimaging Tools and Resources Collaboratory (NITRC) is a neuroimaging informatics knowledge environment for MR, PET/SPECT, CT, EEG/MEG, optical imaging, clinical neuroinformatics, imaging genomics, and computational neuroscience tools and resources.

Comprehensive tutorials and lecture notes covering various aspects of scientific computing using Python and Scipy.

EasyBuild is a software installation framework that allows administrators to easily build and install software on high-performance computing (HPC) systems. It supports a wide range of software packages, toolchains, and compilers. Supported software are found in the EasyConfigs repository, one of several resositories in EasyBuild project.

Thrust is a CUDA library that optimizes parallelization on the GPU for you. The Thrust tutorial is great for beginners. The documentation is helpful for anyone using Thrust.

The free online book for the mlr3 machine learning framework for R. Gives a comprehensive overview of the package and ecosystem, suitable from beginners to experts. You'll learn how to build and evaluate machine learning models, build complex machine learning pipelines, tune their performance automatically, and explain how machine learning models arrive at their predictions.

With the recent uprising of LLM's many business are looking at way to adopt these LLMs and fine-tuning these models on specfic data sets to ensure accuracy. These models when fine-tuned can be optimal for fulfilling the specific needs of a company. This site explains explicitly when, how, and why models should be trained. It goes over various strategies for LLM fine -tuning.

A comprehensive collection of NERSC developed training and tutorial events, offered on regular schedules. All sessions are archived, including slide decks, video recordings, and software examples as are available. Some examples of past training and tutorial topics are listed below Deep Learning for Sciences Webinar Series BerkeleyGW Tutorial Workshop VASP Trainings Timemory Software Monitoring Tutorial, April 2021 HPCToolkit to Measure and Analyzing GPU Applications Performance Tutorial Totalview Tutorial NVidia HPCSDK - OpenMP Target Offload Training Parallelware Training Series ARM Debugging and Profiling Tools Tutorial Roofline on NVIDIA GPUs GPUs for Science events 3-part OpenACC Training Series 9-part CUDA Training Series

Representation learning is a fundamental concept in machine learning and artificial intelligence, particularly in the field of deep learning. At its core, representation learning involves the process of transforming raw data into a form that is more suitable for a specific task or learning objective. This transformation aims to extract meaningful and informative features or representations from the data, which can then be used for various tasks like classification, clustering, regression, and more.

Proxmox Virtual Environment is a hyper-converged infrastructure open-source software. It is a hosted hypervisor that can run operating systems including Linux and Windows on x64 hardware.