Ninth Annual Texas A&M Research Computing Symposium

Last Update: May 14, 2026

Symposium Details

Dates: May 13-15, 2026
Location: Talks and Workshops - Texas A&M Innovative Learning Classroom Building (ILCB), College Station, TX (map)
Parking: Fee-based Parking is available at the Stallings Blvd Garage (SBG) adjacent to the ILCB building (map)
Questions? Call us at (979) 458-8414 or email [email protected]

Texas A&M's High Performance Research Computing is hosting a series of talks and Workshops May 13-15, 2026 to showcase the A&M community’s work in high-performance computing and data-intensive research.

The Symposium will feature a keynote presentation on the National Artificial Intelligence Research Resource (NAIRR) Pilot and a presentation for VISION, The Texas A&M University System DGX SuperPOD featuring 760 NVIDIA H200 GPUs.

Check back regularly for updated details on speakers, workshops, and the agenda.

Keynote Talk:

Katie Antypas, Senior Advisor for Cyberinfrastructure, National Science Foundation

Presentation on VISION, The Texas A&M University System DGX SuperPOD featuring 760 H200 GPUs

Banquet and Poster Session with a prize for best poster

Speakers

Dr. Brendan Roark, Associate Vice President for Research, Texas A&M University
Prof. Daniel Tabor, Chemistry, Texas A&M University
Prof. Wonmuk Hwang, Biomedical Engineering, Texas A&M University
Prof. Phanourios Tamamis, Chemical Engineering, Texas A&M University
Dr. Lars Koesterke, Texas Advanced Computing Center
Dr. Omar Sallam, Argonne National Laboratory
Dr. Alejandro Aviles Sanchez, Texas A&M University

Workshops on AI/ML, GPU Programming, Generative AI, and more

AI Fundamentals, Instructor: Dr. Yalong Pi, TAMIDS
Introduction to GPU programming with OpenMP Offloading, Instructor: Dr. Lars Koesterke, TACC
Generative AI for Protein Design: A Hands-On Introduction to RFdiffusion, Instructor: Dr. Dinesh Devarajan, HPRC
Setting up environments for AI research and Software Development, Instructor: Dr. Thang Ha, HPRC
AI/ML in the Life Sciences, Instructor: Dr. Wesley Brashear, HPRC

Keynote Talk

The National AI Research Resource (NAIRR) Pilot

Katie Antypas, Senior Advisor for Cyberinfrastructure, National Science Foundation (NSF)

Bio: Katie is the Senior Advisor for Cyberinfrastructure at NSF. Prior to joining NSF Katie was at the National Energy Research Scientific Computing (NERSC) Center at Lawrence Berkeley National Laboratory for 17 years in a variety of roles including NERSC Division Deputy, Project Director for NERSC's large scale High Performance Computing system acquisitions, Director of Hardware and Integration of the Exascale Computing Project, Data Department Head and User Services Group Lead. Before coming to NERSC in 2006, Katie worked at the Flash Center at the University of Chicago on the FLASH code, a highly scalable, parallel, adaptive mesh refinement astrophysics application. She has an M.S. in Computer Science from the University of Chicago and a bachelors in Physics from Wellesley College.

Workshops

AI Fundamentals

Friday, May 15, 9:00 AM - 5:00 PM

Instructor: Dr. Yalong Pi, Texas A&M Institute of Data Science

This full-day workshop covers the essential neural network fundamentals and tools to apply deep learning models through hands-on computer vision and natural language processing exercises. The HPC cluster will host and accelerate a set of Jupyter notebooks for image classification, transfer learning, natural language tokenization and embedding, and translation transformer. Both TensorFlow and PyTorch libraries will be used to enhance the understanding of AI and HPRC. A joint TAMIDS and HPRC certification will be provided at the end of the workshop.

• Develop an understanding of concepts of neural networks and machine learning.
• Apply simple convolutional neural network (CNN) models and evaluate their performance.
• Understand the mathematical nature of tokenization and embedding for large language models.
• Explain what attention mechanisms, transformer models, and generative pretrained transformers (GPT).

• American sign language image classification with Tensorflow
• Dog breed image classification and transfer learning with PyTorch
• Text tokenization and embedding
• Attention mechanism, transformer architecture, GPT, and beyond

• Current ACCESS ID
• Basic Python skills

Introduction to GPU programming with OpenMP Offloading

Friday, May 15, 9:00 AM - 12:00 PM

Instructors: Dr. Lars Koesterke, Texas Advanced Computing Center

This workshop introduces OpenMP GPU offloading through practical examples in C/C++ and Fortran. Participants will learn how target regions execute on accelerators, how data is mapped and moved between host and device, and how OpenMP constructs such as teams, distribute, and loop are used to organize work on GPUs. The course also covers common mistakes, basic verification techniques, and introductory asynchronous offloading concepts.

• understand how OpenMP target regions execute on GPUs
• use key constructs for offload, including data mapping and loop/work distribution
• manage device data movement and persistence efficiently
• verify offload behavior and avoid common mistakes

• OpenMP offloading basics: target, execution model, and host/device behavior
• Data mapping and movement: implicit/explicit mapping, target data, enter/exit/update
• Parallel work distribution on GPUs: teams, distribute, parallel for, loop
• Debugging and performance basics: verification, common pitfalls, and asynchronous offload

• Active ACCESS ID
• Basic knowledge of C/C++ or Fortran is preferred

• prior OpenMP experience is recommended
• basic understanding of GPU execution and host/device memory is helpful
• familiarity with Python is helpful for participants without a strong background in compiled languages. It can provide an accessible entry point, and Python is expected to be supported in a future OpenMP standard

Generative AI for Protein Design: A Hands-On Introduction to RFdiffusion

Friday, May 15, 9:00 AM - 12:00 PM

Instructor: Dr. Dinesh Devarajan, Texas A&M High Performance Research Computing

This workshop provides hands-on introduction to diffusion-based generative models for protein design, with a focus on RFdiffusion. Participants will learn how to run RFdiffusion inference workflows on HPRC clusters. The session will introduce the computational workflow, strategies for generative design runs on HPC infrastructure.

• Understand how diffusion models such as RFdiffusion enable de novo protein design
• Learn how RFdiffusion inference workflows are executed on HPC systems

Topics:

• Set up and run RFdiffusion inference through guided, hands-on exercises
• Modify RFdiffusion input parameters (motifs, length, symmetry, structural constraints) to guide protein backbone generation
• Interpret and visualize RFdiffusion outputs

• Current ACCESS ID
• Linux/Unix skills

Setting up environments for AI research and Software Development

Friday, May 15, 1:00 PM - 4:00 PM

Instructors: Dr. Thang Ha, Texas A&M High Performance Research Computing

Have you ever found a GitHub repo that has some features relevant to your research but you could not follow the instructions to make it work on HPRC Linux supercomputers? Maybe you tried to follow the instructions to set up a some Python/Conda environment for such a repo and ended up locked out of your account because you filled up your home storage quota limit? Ever tried to install an R library package or compile a source code in C/C++/Fortran and bumped into errors involving missing libraries that you don't have sudo permission to install? If you encounter any of these issues, this workshop is for you!

By learning to set up environments for Python/R scripts and C/C++/Fortran software compilation on HPC, participants will be able to install the libraries and packages required for their R and Python scripts (e.g. PyTorch), compile source codes into executable programs, and run these scripts and programs on TAMU HPC systems. These skills will be relevant for researchers in a variety of fields, including those involved with AI/ML, molecular dynamics simulations, and materials science.

• Set up a Python virtual environment containing PyTorch, which is a widely-used python package for many common AI/ML workloads, such as Large Language Models (LLMs), using HPRC's in-house Python virtual environment manager "ModuLair", which is based on Python venv.
• Set up a Conda/Mamba environment, in case a given Python environment requires Conda and/or is too complicated to set up using Python venv.
• Set up an environment for running R scripts using HPRC's in-house R project environment management and software module "R_tamu".
• Set up a software compilation environment using a FOSS (GNU) toolchain and/or an Intel toolchain, compile source code into executable programs, and write and submit a Slurm job script to run those compiled programs on HPRC.

• Current ACCESS ID

AI/ML in the Life Sciences

Friday, May 15, 1:00 PM - 4:00 PM

Instructor: Dr. Wesley Brashear, Texas A&M High Performance Research Computing

This workshop explores how AI/ML has become a transformative force in biological research with hands-on applications used in modern life science workflows, from protein structure prediction and variant calling to image-based analysis. Participants will gain practical experience running tools such as AlphaFold3, AlphaFast, and DeepVariant on high-performance computing (HPC) systems, while also learning how to build and interpret basic deep learning models.

• Learn how Artificial Intelligence and Machine Learning (AI/ML) have played a role in past biological research
• Learn how current AI/ML and Deep Learning technologies are being incorporated into modern workflows
• Learn how to access AI/ML-enabled tools on HPRC systems
• Learn how to run and interpret AlphaFold 3 and AlphaFast
• Learn how to run Google’s DeepVariant using NVIDIA’s GPU-accelerated Parabricks software suite
• Learn how to build basic Convolutional Neural Networks for image recognition and classification

• History of AI/ML in biological research
• Running AlphaFold3/AlphaFast on an HPC system
• Running DeepVariant on an HPC system
• Building CNN’s in Jupyter Lab on an HPC system

• Current ACCESS ID
• Familiarity with Python
• Download the AlphaFold3 model parameters file: https://github.com/google-deepmind/alphafold3 (Requests to download the parameters can take 1 or more business days)

Research Computing Symposium Full Schedule (All times are CT)

Last Update: May 14, 2026

Posters

Thank you to our 2026 Sponsors!

Texas A&M Research Computing Symposium is supported in part by NSF award #2112356, ACSS: ACES - Accelerating Computing for Emerging Sciences and NSF award #2430335.