Knowledge Base Resources

Spack is a package manager for supercomputers that can help administrators install scientific software and libraries for multiple complex software stacks.

A tutorial on the effective use of Dask on HPC resources. The four-hour tutorial will be split into two sections, with early topics focused on novice Dask users and later topics focused on intermediate usage on HPC and associated best practices. The knowledge areas covered include (but are not limited to): Beginner section High-level collections including dask.array and dask.dataframe Distributed Dask clusters using HPC job schedulers Earth Science data analysis using Dask with Xarray Using the Dask dashboard to understand your computation Intermediate section Optimizing the number of workers and memory allocation Choosing appropriate chunk shapes and sizes for Dask collections Querying resource usage and debugging errors

Documentation and research based on the latest NLP text generation detection methods for 2023.

An introduction to Cloud Computing

Workshop for beginners and intermediate students in MPI which includes helpful exercises. Open MPI documentation.

Windows Subsystem for Linux (WSL) provides a Linux environment for Windows users to access HPC resources fast and efficiently.

VSCode is a popular IDE that runs on Windows, MacOS, and Linux. This tutorial will explain how to get set up with VSCode to code in Python. It will also provide a tutorial on how to set up Github integration within VSCode.

Background: Big data, defined as having high volume, complexity or velocity, have the potential to greatly accelerate research discovery. Such data can be challenging to work with and require research support and training to address technical and ethical challenges surrounding big data collection, analysis, and publication. Methods: The present study was conducted via a series of semi-structured interviews to assess big data methodologies employed by CU Boulder researchers across a broad sample of disciplines, with the goal of illuminating how they conduct their research; identifying challenges and needs; and providing recommendations for addressing them. Findings: Key results and conclusions from the study indicate: gaps in awareness of existing big data services provided by CU Boulder; open questions surrounding big data ethics, security and privacy issues; a need for clarity on how to attribute credit for big data research; and a preference for a variety of training options to support big data research.

As LLMs get larger fine-tuning to the full extent can become difficult to train on consumer hardware. Storing and deploying these tuned models can also be quite expensive and difficult to store. With PEFT (parameter -efficent fine tuning), it approaches fine-tune on a smaller scale of model parameters while freezing most parameters of the pretrained LLMs. Basically it is providing full performance that which is similar if not better than full fine tuning while only having a small number of trainable parameters. This source explains that as well as going over LORA diagrams and a code walk through.

This tutorial introduces the use of Containers using the Charliecloud software suite. This tutorial will provide participants with background and hands-on experience to use basic Charliecloud containers for HPC applications. We discuss what containers are, why they matter for HPC, and how they work. We'll give an overview of Charliecloud, the unprivileged container solution from Los Alamos National Laboratory's HPC Division. Students will learn how to build toy containers and containerize real HPC applications, and then run them on a cluster. Exercises are demonstrated using the ACES cluster, a composable accelerator testbed at Texas A&M University. Students with an allocation on the ACES cluster can follow along with the ACES-specific exercises.

Neurodesk provides a containerised data analysis environment to facilitate reproducible analysis of neuroimaging data. Analysis pipelines for neuroimaging data typically rely on specific versions of packages and software, and are dependent on their native operating system. These dependencies mean that a working analysis pipeline may fail or produce different results on a new computer, or even on the same computer after a software update. Neurodesk provides a platform in which anyone, anywhere, using any computer can reproduce your original research findings given the original data and analysis code.

Listing of upcoming ACCESS related events and training activities.

InsideHPC is an informational site offers videos, research papers, articles, and other resources focused on machine learning and quantum computing among other topics within high performance computing.

Python course offered by Texas A&M HPRC

Introduction to the Slurm Workload Manager for users and system administrators, plus some material for Slurm programmers.

Data visualization is a critical aspect of data analysis. It allows for a clear and concise representation of data, making it easier for users to understand and interpret complex datasets. One of the most popular libraries for data visualization in Python is Matplotlib. The included website aims to provide a brief overview of Matplotlib, its features, and examples/exercises to dive deeper into its functionalities.

A master’s degree in data science helps prepare professionals to take the next career step. This article will focus primarily on data science, a graduate degree in this field, and a data scientist or data analyst career. With many employers preferring a master’s degree in data science for those seeking to fill roles as data scientists or analysts, we will discuss the data science master’s degree in detail.

VisIt is a prominent open-source, interactive parallel visualization and graphical analysis tool predominantly used for viewing scientific data. Its GitHub repository offers a detailed insight into the software's source code, documentation, and contribution guidelines. In particular, it offers useful examples on how it

Introduction seminar for new reactive python notebook from marimo ambassador.

5 Days of recordings of Python data analysis and visualization training.

Pluses and challenges of mentor selection. Offers tips for acquiring a mentor (finding, asking). And how to be a good mentee. SMART framework mentioned. Discrimination mentioned. Difference between mentor and sponsor underlined. More than one mentor encouraged. Good tips.

Gaussian 16 is a computational chemistry package that is used in predicting molecular properties and understanding molecular behavior at a quantum mechanical level.

Upcoming training events and archives of training materials detailing general HPC best practices as well as how to use OLCF resources and services.

A tutorial paper that presents a generic message-passing algorithm, the sum-product algorithm, that operates in a factor graph. Following a single, simple computational rule, the sum-product algorithm computes either exactly or approximately various marginal functions derived from the global function. A wide variety of algorithms developed in artificial intelligence, signal processing, and digital communications can be derived as specific instances of the sum-product algorithm, including the forward/backward algorithm, the Viterbi algorithm, the iterative "turbo" decoding algorithm, Pearl's (1988) belief propagation algorithm for Bayesian networks, the Kalman filter, and certain fast Fourier transform (FFT) algorithms