Skip to main content

3 posts tagged with "gpus"

View All Tags

May 2025 Maintenance Update

· 7 min read
Kristen Finch
Kristen Finch
HPC Staff Scientist

During May's maintenance, we've refreshed the operating system images for both login and compute nodes with the latest Linux security updates and patches, and enhanced the node image to include NVIDIA Fabric Manager and software upgrades for next-generation GPU switching fabrics. There’s still time to register for GPU in EDU on Thursday, May 15th, 10:00 a.m.–4:00 p.m., where we team up with NVIDIA and Cambridge Computer for a day of demos, teaching guidance, and research highlights. Stay informed by subscribing to our mailing list and the UW-IT Research Computing Events Calendar. The next maintenance is scheduled for Tuesday June 10, 2025 (AKA the 2nd Tuesday of the month).

Notable Updates​

  • Operating system - The images for both the login and compute nodes have been refreshed to incorporate the latest Linux OS security updates and system patches.
  • Node image enhancements - This version of the node image includes NVIDIA Fabric Manager and software upgrades necessary to support next-generation GPU switching fabrics.

Upcoming Events​

Subscribe to event updates and bookmark our UW-IT Research Computing Events Calendar.

  • There's still time to sign up for GPU in EDU Thursday May 15th 10:00 a.m. - 4:00 p.m.
    • Join us for a full day of learning about GPUs with experts from NVIDIA and Cambridge Computer. The event will feature recommendations for building GPU workflows, guidance for using GPUs for teaching, highlights of GPU-powered research at UW, and more. Don’t miss it — Lunch is provided! Registration is still open!

Spring Office Hours​

If you would like to request 1 on 1 help, please send an email to help@uw.edu with "Hyak Office Hour" in the subject line to coordinate a meeting.

Training Resources​

Opportunities​

Computing Training from eScience and more​

eScience logo.
  • Intro Programming Workshop - eScience is holding a Software Carpentry workshop on May 27th–30th (9:00 a.m. – noon each day). The workshop will teach software tools that can make researchers more effective, automate research tasks, and track research over time. Specifically, the Unix Shell, Git, and Python will be taught with a focus on reproducible research. Register here.
  • Teach your own LLM - On Friday, May 23rd from 10:30 - noon in the Open Scholarship Commons, Jose Cols will lead the workshop “Teach your own LLM: Fine-tuning Models on Custom Datasets” covering how LLMs work and how to fine-tune a Llama 3 model for tasks like sentiment analysis and summarization.

External Training Opportunities​

  • COMPLECS: Using Regular Expressions with Linux Tools - Thursday, May 29, 2025 - 11:00 a.m. – 12:30 p.m. (Pacific Time) Regular expressions (regexes) provide a way to identify strings that match a specified pattern. They are extremely useful for preprocessing text and extracting results from high-performance computing and data science workloads. Primarily in the context of the Linux grep utility, we incrementally introduce the main features of regexes: string literals, specifying multiple characters, quantifiers, wildcards, anchors, character classes, grouping, and alternation. We also explore more advanced topics such as word boundaries, lazy and greedy matching, regex flavors (basic, extended, and Perl compatible), regexes with awk and sed, searching compressed files, and using large language models (LLMs) to create regexes. Register here!
  • 8:00 - 11:30 am (Pacific time), Wednesday, May 28, 2025 - LANL is hosting an Accelerated Python Tutorial, presented by Scot Halverson from Nvidia. This will include measuring, understanding, and improving performance of their python applications, including ML workflows using PyTorch and Tensorflow. This event is open to NERSC users. Learn more and register.
  • Building GPU-Accelerated Differentiable Simulations with NVIDIA Warp Python 1- 4 pm (Pacific time), Wednesday, May 28, 2025 - LANL is hosting a Building GPU-Accelerated Differentiable Simulations with NVIDIA Warp Python training, presented by Eric Shi from Nvidia. This approach lets developers harness GPU performance while maintaining the simplicity and flexibility of Python. This event is open to NERSC users. Learn more and register.
  • NERSC GPU Hackathon - NERSC, in conjunction with NVIDIA and the OpenACC organization, will be hosting an Open Hackathon from July 16th-18th with an opening day on July 9th as part of the annual Open Hackathon Series. Please note the deadline to submit a proposal is 11:59 PM Pacific, May 28, 2025. So apply now! Learn more.
  • A Deep Dive into the HPC SDK - 1:00 - 4:00 pm (Pacific time), Thursday, May 29, 2025 - LANL is hosting a Deep Dive into the Nvidia HPC SDK Training, presented by Scot Halverson from Nvidia. This talk will cover the broad set of compilers, tools, and libraries that make up the NVIDIA HPC SDK. This event is open to NERSC users. Learn more and register.
  • High Throughput Workflow Tools and Strategies - 8:30 am - 12:00 pm (Pacific time), Friday, May 30, 2025 - NERSC is hosting an online webinar presented by William Arndt of NERSC and Geoffrey Lentner from Advanced Computing, Purdue University. This training session will discuss and demonstrate multiple software tools for managing high throughput workloads: GNU Parallel, Snakemake, and Hypershell. The seminar is open to the general public. Learn more and register.
  • Solving Data Management Challenges with Globus - June 6, 2025, 9 a.m. – 12 p.m. (Pacific Time) Participants will engage in hands-on exercises to explore how Globus can streamline data movement across cloud and high-performance computing systems. Whether managing large datasets, enabling secure collaboration, or automating workflows, this session will equip participants with the knowledge and skills to maximize the benefits of Globus. Enroll here.
  • COMPLECS: Code Migration - Thursday, June 12, 2025 - 11:00 a.m. – 12:30 p.m. (Pacific Time) We will cover typical approaches to moving your computations to HPC resources: using applications/software packages already available on the system through Linux environment modules; compiling code from source with information on compilers, libraries, and optimization flags to use; setting up Python and R environments; using conda-based environments; managing workflows; and using containerized solutions via Singularity. Register here!
  • Automating Research with Globus: The Modern Research IT Platform - Aug. 18, 2025, 9 a.m. – 12 p.m. (Pacific Time) This workshop introduces Globus Flows and its role in automating research workflows. Participants will explore data portals, science gateways, and commons, enabling seamless data discovery and access. Enroll here.

If you have any questions about using Hyak, please start a help request by emailing help@uw.edu with "Hyak" in the subject line.

Happy Computing,

Hyak Team

April 2025 Maintenance Update

· 10 min read
Kristen Finch
Kristen Finch
HPC Staff Scientist

April maintenance included the latest OS patches and security enhancements for login and compute nodes, along with testing endpoint detection and response (EDR) software to strengthen cluster security. We would like to bring your attention to upcoming events featuring an AWS AI in Research Workshop (April 17), our annual Research Computing Club Hackathon (April 19), and the Kopah S3 Storage Launch Event "Data Storage Day" (May 5), showcasing campus-wide S3-compatible storage. Additionally, GPU in EDU (May 15) will provide insights into GPU workflows demonstrated by experts at Cambridge Computer and NVIDIA. Regular office hours are available for research computing support. Stay informed through training resources, event subscriptions, and the UW-IT Research Computing Events Calendar. The next maintenance is scheduled for Tuesday May 13, 2025 (AKA the 2nd Tuesday of the month).

Notable Updates, New Features​

  • Operating system - The login and compute node images were updated to address system patches and security updates in the Linux operating system (OS).
  • Security solutions testing - We tested endpoint detection and response (EDR) software as a potential solution for an enhanced cluster security posture. This testing is part of our ongoing efforts to maintain a secure computing environment in line with funding requirements (e.g., NIST-800, CMMC, HIPAA, NIH).
  • Globus - We’re excited to announce that Globus has been added to Hyak Klone and Kopah S3. Globus makes it easy to transfer large datasets reliably and securely between systems, whether across campus or around the world. With features like automated transfers, fault tolerance, and a simple web interface, it’s a powerful tool for streamlining data movement in research workflows.

Upcoming Training and Events​

Subscribe to event updates and bookmark our UW-IT Research Computing Events Calendar.

  • AWS AI in Research Workshop - UW-IT Research Computing and eScience Institute will host a workshop introducing how AWS enables AI in research on Thursday, April 17th from 12:00 - 4:00 p.m. in the eScience Institute. Whether you are developing your own models, building off existing models, or you need to implement generative AI, AWS has you covered. Bring your laptop and join us for a couple of engaging sessions followed by a hands-on lab building AI agents. Learn more.

  • RCC Hackathon - The Research Computing Club (RCC), in collaboration with UW-IT Research Computing and the eScience Institute, is excited to host an all-day HPC Hackathon on Saturday, April 19th from 10:00 a.m. – 6:00 p.m. in the eScience Institute. Learn more.

  • Discover Kopah: Your New S3-Compatible Campus Storage Solution at Data Storage Day! Join us on Monday, May 5 from 1:00 – 5:00 p.m. in the eScience Institute for the official Kopah S3 Storage Service Launch Event — your gateway to fast, scalable storage right on campus. Whether you're a researcher handling big data, an instructor managing course materials, or simply someone in need of reliable cloud-like storage, Kopah is designed for everyone. This event will feature live demos of S3-compatible tools like s3cmd, Globus, JuiceFS, Cyberduck, and boto3, and staff will be available to help you get started with Kopah S3. Learn more.

  • GPU in EDU Save the Date Thursday May 15th 10:00 a.m. - 4:00 p.m. – Join UW-IT Research Computing for a day learning about GPUs from the experts at NVIDIA and Cambridge Computer. This event will feature live demonstrations for building your GPU workflows, recommendations for incorporating GPUs into instruction, computing research at UW, and more! Registration link coming soon!

Spring Office Hours​

If you would like to request 1 on 1 help, please send an email to help@uw.edu with "Hyak Office Hour" in the subject line to coordinate a meeting.

Training Resources​

Opportunities​

External Training Opportunities​

  • Parallel Computing with MATLAB: Hands on workshop Coming Up April 16 1PM PDT - During this hands-on workshop, we will introduce parallel and distributed computing in MATLAB with a focus on speeding up application codes and offloading computers. By working through common scenarios and workflows using hands-on demos, you will gain a detailed understanding of the parallel constructs in MATLAB, their capabilities, and some of the common hurdles that you'll encounter when using them. SIGN UP! Highlights:

    • Multithreading vs multiprocessing
    • When to use parfor vs parfeval constructs
    • Creating data queues for data transfer
    • Leveraging NVIDIA GPUs
    • Parallelizing Simulink models
    • Working with large data

  • AI in Science Postdoc Workshop - Generative AI systems built upon large language models (LLMs) show great promise as tools that enable people to access information through natural conversation. Scientists can benefit from the breakthroughs these systems enable to create advanced tools that will help accelerate their research outcomes. Last week the UW Scientific Software Engineering Center (SSEC) offered a Generative AI / RAG training opportunity to the Schmidt AI in Science Postdoctoral Fellows. The online tutorial focused on how to utilize the underlying methods in Generative AI to advance scientific research, including the basics of LLMs followed by a demo of using LLMs and RAG for creating a question answering tool based on private data. Learn more.

  • Trainings from Texas A&M University - gain skills that are transferrable to Hyak (Linux, Slurm job scheduler, Open OnDemand, NVIDIA GPU).

    • ACES: Python for Data Science 04/11/25 - 10:00 AM - 04:00 PM CDT - This short course for experienced programmers introduces the Numpy, Pandas, and Matplotlib libraries commonly used to manage and display large datasets in Python. Exercises will be performed in the learner's web browser in Jupyter Notebooks running in the Open OnDemand portal of the ACES cluster. More information about this course at https://hprc.tamu.edu/training/aces_python4data.html.
    • ACES: Metagenomics 04/15/25 - 01:30 PM - 04:00 PM CDT - This short course introduces concepts of metagenomic analyses based on data generated by Next Generation Sequencing (NGS) technology using ACES cluster, a composable accelerator testbed at Texas A&M University. Students will learn to complete a metagenomics pipeline using QIIME2 software. Read more at https://hprc.tamu.edu/training/aces_metagenomics.html
    • ACES: Rust 04/22/25 - 10:00 AM - 12:30 PM CDT - This short course provides an introduction to Rust, a modern systems programming language known for its safety, speed, and concurrency, through hands-on coding exercises and practical examples using the ACES cluster, a composable accelerator testbed at Texas A&M University. Learn more at https://hprc.tamu.edu/training/aces_rust.html
    • ACES: GPU Programming (CUDA) 04/22/25 - 01:30 PM - 04:00 PM CDT - This short course covers basic topics in CUDA programming on NVIDIA GPUs. More information about this Short Course https://hprc.tamu.edu/training/intro_cuda.html Topics include:
      • CUDA architecture
      • basic language usage of CUDA C/C++
      • writing, executing CUDA code.
    • ACES: Python for HPC and Advanced Topics 04/25/25 - 10:00 AM - 04:00 PM CDT - This short course for experienced Python programmers will cover several topics relevant to Python workloads running on HPC systems, including environment and data handling. Exercises will be performed in the learner's web browser in Jupyter Notebooks running in the Open OnDemand portal of the ACES cluster. More information about this course at https://hprc.tamu.edu/training/aces_python4HPC.html.

  • Trainings from the National Energy Research Scientific Computing Center (NERSC) - gain skills that are transferrable to Hyak

    • NERSC N-Ways to GPU Programming Bootcamp - NERSC, in collaboration with the OpenACC Organization and NVIDIA, is hosting an N-Ways to GPU Programming Bootcamp for 3 days from Wednesday, April 30 to Friday, May 2. Beginner users in GPU programming are especially encouraged to attend. This is a virtual event. For detailed information, and how to apply, please refer to Open Hackathons's Bootcamp Events page. The application deadline is April 13, 2025.
    • Building GPU-Accelerated Differentiable Simulations with NVIDIA Warp Python 1- 4 pm (Pacific time), Wednesday, May 28, 2025 - LANL is hosting a Building GPU-Accelerated Differentiable Simulations with NVIDIA Warp Python training, presented by Eric Shi from Nvidia. Warp is a Python framework designed for authoring high-performance, GPU-accelerated code directly in Python. At its core, Warp uses a programming model where Python functions are just-in-time (JIT) compiled into efficient code that can run on both CPUs and NVIDIA GPUs, using C++/CUDA as an intermediate representation. This approach lets developers harness GPU performance while maintaining the simplicity and flexibility of Python. Learn more and register.
    • NERSC GPU Hackathon - NERSC, in conjunction with NVIDIA and the OpenACC organization, will be hosting an Open Hackathon from July 16th-18th with an opening day on July 9th as part of the annual Open Hackathon Series. The NERSC Open Hackathon will be hosted as a hybrid event. Days 0-1 (July 2 and 9) will be held virtually, and attendees will have the option to attend Days 2-4 (July 16 - 18) either in-person at NERSC or online. This hackathon is open to everyone looking to take their projects to the next level; however, priority acceptance will be given to NERSC collaborators. Please note the deadline to submit a proposal is 11:59 PM Pacific, May 28, 2025. So apply now! Please note acceptance is not confirmed until you have received a confirmation email. Learn more.
    • More opportunities from NERSC

Jobs​

  • The UW Echospace research group is seeking a student or an early career professional to help develop open-source scientific software for processing large-scale ocean sonar data to accelerate marine ecosystem research. APPLY!

  • Metascience & AI Postdoctoral Fellowship - The Sloan Foundation is awarding grants of up to $250k to support early career researchers in the social sciences and humanities who are interested in understanding the implications of AI for the science and research ecosystem. Applicants are required to have a faculty mentor based at the research organization where the grant is to be held. Feel free to reach out to eScience for support with identifying a potential UW mentor. Applications due April 10, 2025! Learn more.

  • The Center for Geospatial Intelligence at George Mason University is looking for a Postdoctoral Research Fellow in geospatial data science and machine learning to work on research projects related to large-scale urban simulations and geospatial machine learning. APPLY!

  • Yale Center for Research Computing is hiring an HPC System Administrator to join the center’s Engineering team to provide hardware and software administration for a growing number of high performance computing (HPC) clusters used in faculty research. This position will support the infrastructure behind all of the above, including hardware, system and resource-management software, networking, storage, monitoring and security measures. This is a highly-collaborative effort, so frequent interaction with other system administrators, research support staff, management, vendors and researchers is a regular part of the role. Learn more.

  • Job opening for a High Performance Computing (HPC) Research Computing Associate at Colby College in Maine. Learn more.

If you have any questions about using Hyak, please start a help request by emailing help@uw.edu with "Hyak" in the subject line.

Happy Computing,

Hyak Team

March 2025 Maintenance Details

· 5 min read
Kristen Finch
Kristen Finch
HPC Staff Scientist

March maintenance is complete, and Klone is back in operation. Notable updates from this maintenance include new features and documentation (VS Code via Open OnDemand), upcoming events (SAVE THE DATE for Hackathon and GPU Day), newly-released training videos (Advanced Slurm), office hours, and opportunities from the national computing community! The next maintenance is scheduled for Tuesday April 8, 2025 (AKA the 2nd Tuesday of the month).

Notable Updates​

  • Operating system - The login and compute node images were updated to address system patches and security updates in the Linux operating system (OS).
  • Hardware - The HPC engineering team used this scheduled time to perform what would have otherwise been disruptive tasks by physically re-arranging equipment within the data center in preparation for a future (GPU) cluster launch. A new rack was also prepared for a bulk expansion of HPC compute node capacity.

New Features and Documentation​

  • Our GPU documentation section has an additional worked example for preparing a software container to utilize Hyak GPUs. Check out the new content.
  • VS Code has been added as an interactive application via Hyak’s Open OnDemand Platform. Go to Open OnDemand(VPN required if off campus) and view the supporting documentation.
  • Have you ever wanted to contribute documentation or tutorials to support your fellow Hyak users? By preparing a GitHub CodeSpace and containerized development environment, we have made contributing to Hyak’s documentation website and repository more accessible. We invite and appreciate your feedback and contributions, no matter how small. Check out our guide for using the development container and submitting your contributions via a Pull Request.

Upcoming Training and Events​

  • The Research Computing Club (RCC) is hosting a Hackathon on Saturday April 19 10am-5pm. The RCC officers have prepared a set of modules for participants to work through together in small groups. Lunch will be provided. Registration is required. Additional details coming soon.
  • GPU Day Thursday May 15 SAVE THE DATE! hosted by UW-IT Research Computing featuring hands-on demonstrations from Cambridge Computer and NVIDIA. Time and venue TBA. Stay tuned for more details and links to register.

New training videos uploaded​

Hyak: Advanced Slurm recording from training on February 25. This tutorial demonstrates these benefits of Slurm and provide you with some template Slurm scripts that you can adapt for your purposes. Click here for walk through tutorial and training materials.

Check out our Research Computing Training Playlist on UW-IT's YouTube channel.

Winter 2025 Office Hours​

If you would like to request 1 on 1 help, please send an email to help@uw.edu with "Hyak Office Hour" in the subject line to coordinate a meeting.

Opportunities​

  • We're Hiring! The Hyak team is hiring an HPC Staff Scientist to join our team. Use your experience to help Hyak users build capacity especially as we launch out new GPU system this fall. Job description HERE.

  • Join the UW AI Community of Practice on MS Teams to get updates from UW-IT's AI team about events and join the discussion around AI in the news, society, and culture.

  • The Accelerated AI Algorithms for Data-Driven Discovery (A3D3) Institute funded by the National Science Foundation (NSF), under the Harnessing the Data Revolution (HDR) program, is seeking postbaccalaureate research fellows to join our interdisciplinary teams of scientists and engineers to develop and deploy artificial intelligence to accelerate science discoveries in particle physics, astrophysics, biology, and neuroscience. APPLY!

  • The Alfred P. Sloan Foundation is providing a postdoctoral fellowship program to support early career researchers in the social sciences and humanities who are interested in building a career in understanding the implications of AI for the science and research ecosystem. APPLY!

  • eScience is seeking current and incoming UW postdocs who are actively involved in developing or utilizing advanced data science/AI tools and techniques in their research at the UW. Applications are due Saturday, March 15th. APPLY!

  • Tania Malik, a lecturer at the School of Informatics and Cybersecurity, and a director of HPC Nexus lab at TU Dublin, Ireland is looking to support one postdoc under the SUSTAIN-FIT Horizon Europe Programme. If you are passionate about Energy-Efficient High-Performance Computing (HPC) or Green Computing for modern HPC platforms feel free to contact tania.malik@tudublin.ie with your CV and a brief research proposal.

If you have any questions about using Hyak, please start a help request by emailing help@uw.edu with "Hyak" in the subject line.

Happy Computing,

Hyak Team