Knowledge Base Resources
Use these links “vetted” by the community. Additional CI links are always welcome.
Warewulf documentation
0
Warewulf is an operating system provisioning platform for Linux that is designed to produce secure, scalable, turnkey cluster deployments that maintain flexibility and simplicity. It can be used to setup a stateless provisioning in HPC environment.
ACCESS KB Guide - Expanse
0
Expanse at SDSC is a cluster designed by Dell and SDSC delivering 5.16 peak petaflops, and offers Composable Systems and Cloud Bursting.
Setting up PyFR flow solver on clusters
0
These instructions were executed on the FASTER and Grace cluster computing facilities at Texas A&M University. However, the process can be applied to other clusters with similar environments. For local installation, please refer to the PyFR documentation.
Please note that these instructions were valid at the time of writing. Depending on the time you're executing these, the versions of the modules may need to be updated.
1. Loading Modules
The first step involves loading pre-installed software libraries required for PyFR. Execute the following commands in your terminal to load these modules:
module load foss/2022b
module load libffi/3.4.4
module load OpenSSL/1.1.1k
module load METIS/5.1.0
module load HDF5/1.13.1
2. Python Installation from Source
Choose a location for Python 3.11.1 installation, preferably in a .local directory. Navigate to the directory containing the Python 3.11.1 source code. Then configure and install Python:
cd $INSTALL/Python-3.11.1/
./configure --prefix=$LOCAL --enable-shared --with-system-ffi --with-openssl=/sw/eb/sw/OpenSSL/1.1.1k-GCCcore-11.2.0/ PKG_CONFIG_PATH=$LOCAL/pkgconfig LDFLAGS=/usr/lib64/libffi.so.6.0.2
make clean; make -j20; make install;
3. Virtual Environment Setup
A virtual environment allows you to isolate Python packages for this project from others on your system. Create and activate a virtual environment using:
pip3.11 install virtualenv
python3.11 -m venv pyfr-venv
. pyfr-venv/bin/activate
4. Install PyFR Dependencies
Several Python packages are required for PyFR. Install these packages using the following commands:
pip3 install --upgrade pip
pip3 install --no-cache-dir wheel
pip3 install --no-cache-dir botorch pandas matplotlib pyfr
pip3 uninstall -y pyfr
5. Install PyFR from Source
Finally, navigate to the directory containing the PyFR source code, and then install PyFR:
cd /scratch/user/sambit98/github/PyFR/
python3 setup.py develop
Congratulations! You've successfully set up PyFR on the FASTER and Grace cluster computing facilities. You should now be able to use PyFR for your computational fluid dynamics simulations.
Examples of Thrust code for GPU Parallelization
0
Some examples for writing Thrust code. To compile, download the CUDA compiler from NVIDIA. This code was tested with CUDA 9.2 but is likely compatible with other versions. Before compiling change extension from thrust_ex.txt to thrust_ex.cu. Any code on the device (GPU) that is run through a Thrust transform is automatically parallelized on the GPU. Host (CPU) code will not be. Thrust code can also be compiled to run on a CPU for practice.
Machine Learning in Astrophysics
0
Machine learning is becoming increasingly important in field with large data such as astrophysics. AstroML is a Python module for machine learning and data mining built on numpy, scipy, scikit-learn, matplotlib, and astropy allowing for a range of statistical and machine learning routines to analyze astronomical data in Python. In particular, it has loaders for many open astronomical datasets with examples on how to visualize such complicated and large datasets.
Geocomputation with R (Free Reference Book)
0
Below is a link for a book that focuses on how to use "sf" and "terra" packages for GIS computations. As of 5/1/2023, this book is up to date and examples are error free. The book has a lot of information but provides a good overview and example workflows on how to use these tools.
AI/ML TechLab - Accelerating AI/ML Workflows on a Composable Cyberinfrastructure
0
This technology lab contains a set of sessions to help a new user start an AI project on the ACES cluster, a composable accelerator testbed at Texas A&M University. You will learn how to create and activate a virtual environment, manipulate and visualize data with Pandas and Matplotlib, use Scikit-learn for linear regression and classification applications, and use Pytorch to create and train a simple image classification model with deep neural networks (DNN).
How the Little Jupyter Notebook Became a Web App: Managing Increasing Complexity with nbdev
0
A tutorial entitled "How the Little Jupyter Notebook Became a Web App: Managing Increasing Complexity with nbdev" presented at SciPy 2023 in Austin, TX. This tutorial is hosted in a series of Jupyter Notebooks which can be accessed in the click of a button using Binder. See the README for more information.
Higher Ed Controlled Unclassified Information Slack (HigherEdCUI)
0
Slack channel for the Higher Ed CUI community
Performance Engineering Of Software Systems
0
A class from MITOpenCourseware that gives a hands on approach to building scalable and high-performance software systems. Topics include performance analysis, algorithmic techniques for high performance, instruction-level optimizations, caching optimizations, parallel programming, and building scalable systems.
ACCESS Campus Champion Example Allocation
0
ACCESS requests proposals to be written following NSF proposal guidelines. The link provides an example of an ACCESS proposal using an NSF LaTeX template. The request is at the DISCOVER level appropriate for Campus Champions. The file is 2 pages: the first page details the motivation, approach, and resources requested; and the second page is a 1-page bio.
Introduction to GPU/Parallel Programming using OpenACC
0
Introduction to the basics of OpenACC.
Tutorial for OpenMP Building up and Utilization
0
The following link elaborates the usage of OpenMP API and its related syntax. There are also several exercises available for learners to help them get familiar with this widely-used tool for multi-threaded realization.
NCSA HPC-Moodle
0
Self-paced tutorials on high-end computing topics such as parallel computing, multi-core performance, and performance tools. Some of the tutorials also offer digital badges.
Fundamentals of R Programming
0
This course is an introduction to the R programming language and covers the fundamental concepts needed to operate in the R environment. This course was taught for the ACCESS community on September 26, 2023, but the materials for the course are still available on the ACES cluster and can be completed independently. All materials are presented as learnR notebooks and cover several topics, including data types, variables, built-in functions, data structures, and plotting.
FSL Lectures
0
This is the official University of Oxford FSL group lecture page. This includes information on upcoming and past courses (online and in-person), as well as lecture materials. Available lecture materials includes slides and recordings on using FSL, MR physics, and applications of imaging data.
Electric field analyses for molecular simulations
0
Tool to compute electric fields from molecular simulations
Intro to Statistical Computing with Stan
0
The Stan language is used to specify a (Bayesian) statistical model with an imperative program calculating the log probability density function. Here are some useful links to start your exploration of this statistical programming language, and a Python interface to Stan.
Using Dask on HPC Systems
0
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
AI powered VsCode Editor
0
**Cursor: The AI-Powered Code Editor**
Cursor is a cutting-edge, AI-first code editor designed to revolutionize the way developers write, debug, and understand code. Built upon the premise of pair-programming with artificial intelligence, Cursor harnesses the capabilities of advanced AI models to offer real-time coding assistance, bug detection, and code generation.
**How Cursor Benefits High-Performance Computing (HPC) Work:**
1. **Efficient Code Development:** With AI-assisted code generation, researchers and developers in the HPC realm can quickly write optimized code for simulations, data processing, or modeling tasks, reducing the time to deployment.
2. **Debugging Assistance:** Handling complex datasets and simulations often lead to intricate bugs. Cursor's capability to automatically investigate errors and determine root causes can save crucial time in the HPC workflow.
3. **Tailored Code Suggestions:** Cursor's AI provides context-specific code suggestions by understanding the entire codebase. For HPC applications where performance is paramount, this means receiving recommendations that align with optimization goals.
4. **Improved Code Quality:** With AI-driven bug scanning and linter checks, Cursor ensures that HPC codes are not only fast but also robust and free of common errors.
5. **Easy Integration:** Being a fork of VSCode, Cursor allows seamless migration, ensuring that developers working in HPC can swiftly integrate their existing VSCode setups and extensions.
In essence, for HPC tasks that demand speed, precision, and robustness, Cursor acts as an invaluable co-pilot, guiding developers towards efficient and optimized coding solutions.
It is free if you provide your own OPEN AI API KEY.
Jetstream2 Status
0
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.
Pandas - Python
0
pandas is a fast, powerful, flexible and easy to use open source data analysis and manipulation tool, built on top of the Python programming language. It lets you store data in easy to manage and display data frames, with column names and datatypes.
Building the ArduPilot environment for Linux
0
This article provides instructions for building AirSim, an open-source simulator for autonomous vehicles, on Linux. It outlines the steps to build Unreal Engine, clone and build the AirSim repository, and set up the Unreal environment. It also includes information on how to use AirSim and optional setups such as remote control for manual flight.
ACCESS Support Portal
0
Linux Tutorial from Ryan's Tutorials
0
The following pages are intended to give you a solid foundation in how to use the terminal, to get the computer to do useful work for you. You won't be a Unix guru at the end but you will be well on your way and armed with the right knowledge and skills to get you there if that's what you want (which you should because that will make you even more awesome). Here you will learn the Linux command line (Bash) with our 13 part beginners tutorial. It contains clear descriptions, command outlines, examples, shortcuts and best practice. At first, the Linux command line may seem daunting, complex and scary. It is actually quite simple and intuitive (once you understand what is going on that is), and once you work through the following sections you will understand what is going on. Unix likes to take the approach of giving you a set of building blocks and then letting you put them together. This allows us to build things to suit our needs. With a bit of creativity and logical thinking, mixed in with an appreciation of how the blocks work, we can assemble tools to do virtually anything we want. The aim is to be lazy. Why should we do anything we can get the computer to do for us? The only reason I can think of is that you don't know how (but after working through these pages you will know how, so then there won't be a good reason). A question that may have crossed your mind is "Why should I bother learning the command line? The Graphical User Interface is much easier and I can already do most of what I need there." To a certain extent you would be right, and by no means am I suggesting you should ditch the GUI. Some tasks are best suited to a GUI, word processing and video editing are great examples. At the same time, some tasks are more suited to the command line, data manipulation (reporting) and file management are some good examples. Some tasks will be just as easy in either environment. Think of the command line as another tool you can add to your belt. As always, pick the best tool for the job.