Sixth Annual Texas A&M Research Computing Symposium
Last Update: May 17, 2023
Symposium Details
Dates: May 17-19, 2023
Location: Talks and Workshops - Innovative Learning Classroom Building (ILCB) (map)
Questions? Call us at (979) 458-8414 or email help@hprc.tamu.edu
Registration is required
Texas A&M's High Performance Research Computing is hosting a series of talks May 17-19, 2023 to showcase the A&M community’s work in computing and data-intensive research. There will be an opportunity for students to present their work at the poster session.
Keynote talks:
Margaret Martonosi, NSF Assistant Director for CISE
Steven J. Berthel, Ph.D. TBDA Program Manager and Lead Medicinal Chemist. Panorama Global, Seattle WA
Banquet and Poster Session with a prize for best poster
Speakers
Prof. Raymundo Arroyave, Materials Science & Engineering
Prof. Eduardo Gildin, Petroleum Engineering
Prof. Phanourios Tamamis, Chemical Engineering
Prof. Jian Tao, School of Performance, Visualization & Fine Arts
Prof. Sol Milena Mejia Chica, Chemistry, Javeriana University
Dr. Holly Gibbs, Microscopy and Imaging Center, Biomedical Engineering
Dr. Lars Koesterke, Texas Advanced Computing Center
Dr. Greg Zynda, NVIDIA Senior Solutions Architect
Dr. Srivathsan Koundinyan, NVIDIA Software Architect
Robert Loredo, IBM Quantum Ambassador
Workshops on GPU Centric Computing
Data Parallelism: How to Train Deep Learning Models on Multiple GPUs, Instructor: Dr. Srivathsan Koundinyan, NVIDIA Speeding Up Your MATLAB Code, Instructor: Armando Garcia, MathWorks
Deep Learning with MATLAB: A Visual and Intuitive Approach, Instructor: Jon Loftin, MathWorks
Keynote Talks
The Computing and Information Science and Engineering Landscape: A Look Forward
Margaret Martonosi, National Science Foundation’s (NSF) Assistant Director for Computer and information Science and Engineering (CISE)
Abstract: The United States National Science Foundation (NSF) supports a majority of US academic research in the Computer and Information Science and Engineering (CISE) topic areas. A long-time computing researcher herself, Dr. Margaret Martonosi is now serving a 4-year term leading the NSF CISE Directorate, and stewarding the CISE directorate’s $1B+ annual budget on behalf of research, education, workforce and infrastructure funding in CISE topic areas and for science as a whole. In this talk, she will discuss key themes for the field, how CISE is developing programmatic opportunities to advance research related to them, and also how CISE invests in cross-cutting people issues for the field as well.
Bio: Margaret Martonosi leads the US National Science Foundation’s (NSF) Directorate for Computer and information Science and Engineering (CISE). With an annual budget of more than $1B, the CISE directorate at NSF has the mission to uphold the Nation’s leadership in scientific discovery and engineering innovation through its support of fundamental research and education in computer and information science and engineering as well as transformative advances in research cyberinfrastructure. While at NSF, Dr. Martonosi is on leave from Princeton University where she is an endowed chair Professor of Computer Science. Dr. Martonosi's research interests are in computer architecture and hardware-software interface issues in both classical and quantum computing systems. Dr. Martonosi is a member of the National Academy of Engineering and she is a Fellow of the ACM and IEEE.
Tuberculosis Drug Discovery - application of computational approaches in a unique industry/academic collaboration
Steven J. Berthel, Ph.D., Tuberculosis Drug Accelerator (TBDA) Program Manager and Lead Medicinal Chemist. Panorama Global, Seattle WA
Abstract: Despite the fact that, aside from SARS-COV2 infection (COVID19) recently, tuberculosis (TB) has been the deadliest infectious disease in the world for decades, drug discovery and development efforts remain relatively low. Ten years ago, the tuberculosis drug accelerator (TBDA), a novel collaboration between industry and academia, was created in an attempt to address this deficiency. An essential component of any drug discovery effort is the identification of chemical starting points for medicinal chemistry exploration. While hit finding paradigms can run the gamut between rational and random approaches, docking experiments strike a balance between drug design and high throughput screening (HTS). The challenges of finding good starting points for mycobacterial targets and working in a unique dissociated/distributed multi-partner research environment will be discussed with an emphasis on virtual screening.
Bio: Steven J. Berthel earned his B.S. in Chemistry from the University of Connecticut under the direction of Professor James M. Bobbitt and his Ph.D. in Organic Chemistry from Dartmouth College under the direction of Professor Gordon W. Gribble. After a postdoctoral appointment at the Université catholique de Louvain (Belgium) with Professor Leon Ghosez, he joined Hoffmann-La Roche Pharmaceuticals where he spent 20+ years in preclinical research-discovery chemistry rising to the rank of Research Leader. After Roche closed the Nutley NJ site, he moved to Boehringer Ingelheim Pharmaceuticals in Ridgefield CT, where he spent 2.5 years as an Assistant Director in Drug Regulatory Affairs. For the last 5+ years he has worked as the Tuberculosis Drug Accelerator Program Manager and Lead Medicinal Chemist, first for the NewVentureFund and currently at Panorama Global, a 501c3 charity located in Seattle WA. A native New Yorker, he lives in a small town in northern NJ with his wife and two dogs.
Workshops
Data Parallelism: How to Train Deep Learning Models on Multiple GPUs
Wednesday, May 17 8:30AM-4:30PM
Hosted by NVIDIA, Deep Learning Institute
Instructor: Dr. Srivathsan Koundinyan, NVIDIA
Modern deep learning challenges leverage increasingly larger datasets and more complex models. As a result, significant computational power is required to train models effectively and efficiently. Learning to distribute data across multiple GPUs during deep learning model training makes possible an incredible wealth of new applications utilizing deep learning.
Additionally, the effective use of systems with multiple GPUs reduces training time, allowing for faster application development and much faster iteration cycles. Teams who are able to perform training using multiple GPUs will have an edge, building models trained on more data in shorter periods of time and with greater engineer productivity.
This workshop teaches you techniques for data-parallel deep learning training on multiple GPUs to shorten the training time required for data-intensive applications. Working with deep learning tools, frameworks, and workflows to perform neural network training, you’ll learn how to decrease model training time by distributing data to multiple GPUs, while retaining the accuracy of training on a single GPU.
Attendees that complete the training will receive an NVIDIA DLI Certificate
Learning Objectives
By participating in this workshop, you'll learn to:- Understand how data parallel deep learning training is performed using multiple GPUs
- Achieve maximum throughput when training, for the best use of multiple GPUs
- Distribute training to multiple GPUs using PyTorch Distributed Data Parallel
- Understand and utilize algorithmic considerations specific to multi-GPU training performance and accuracy
- PyTorch
- PyTorch Distributed Data Parallel
- NCCL
- Experience with deep learning training using Python
- Experience with PyTorch is preferred, but not required
Speeding Up Your MATLAB Code
Wednesday, May 17 10:00AM-12:00PM
Hosted by MathWorks
Instructor: Armando Garcia
Are you curious about speeding up your computations with MATLAB? In this workshop you will learn about best coding practices for optimized performance including code generation. Also, using practical code examples, you will be introduced to parallel computing in MATLAB for multicore desktop machines, clusters and GPUs. Highlights: refresh best coding practices, identify performance bottlenecks, discover parallel processing constructs for multicore desktop machines, learn about job monitoring and handling, and see how to scale your applications to clusters and clouds.
Attendees will receive a Certificate of Attendance from MathWorks.
About the presenter: Armando Garcia is a Customer Success Engineer for MathWorks. In this role, he partners with university faculty and researchers to help them optimize their use of MATLAB and Simulink in their teaching and research endeavors. Armando has a MS in Engineering Mechanics, 12+ years of combined experience in research and the industry, and in the past has used MATLAB in applications ranging from extracting ultrasonic properties of human skull bone to predicting the performance of pumping equipment.
Deep Learning with MATLAB: A Visual and Intuitive Approach
Wednesday, May 17 1:00PM-3:00PM
Hosted by MathWorks
Instructor: Jon Loftin
In this workshop we will introduce deep learning with MATLAB. We will build a neural network from scratch and modify a previously trained network, using the MATLAB Deep Network Designer. Deep learning is quickly becoming embedded in everyday applications. It’s becoming essential for students and educators to adopt this technology to solve complex real-world problems. MATLAB and Simulink provide a flexible and powerful platform to develop and automate data analysis, deep learning, AI, and simulation workflows in a wide range of domains and industries. The Deep Network Designer allows you to interactively build, visualize, and train neural networks.
Attendees will receive a Certificate of Attendance from MathWorks.
About the presenter:
Full Schedule (All times are CDT)
Last Update: May 17, 2023
| Wed. May 17 | Workshops (ILCB 224 & 237, map) |
|---|---|
| 8:30AM - 12:00PM | Data Parallelism: How to Train Deep Learning Models on Multiple GPUs
Dr. Srivathsan Koundinyan, NVIDIA Software Architect ILCB 224 |
| 10:00AM - 12:00PM | Speeding Up Your MATLAB Code
Armando Garcia, MathWorks ILCB 237 |
| 12:00PM - 1:00PM | Lunch Sponsored by Cambridge Computer |
| 1:00PM - 4:30PM | Data Parallelism: How to Train Deep Learning Models on Multiple GPUs (cont.)
Dr. Srivathsan Koundinyan, NVIDIA Software Architect ILCB 224 |
| 1:00PM - 3:00PM | Deep Learning with MATLAB: A Visual and Intuitive Approach
Jon Loftin, MathWorks ILCB 237 |
| Thurs. May 18 | Keynote, Research Talks (ILCB 224 map) Banquet and Poster Session (ILSB map) |
| 8:15AM - 8:50AM | Check-in |
| 8:50AM - 9:00AM | Opening Remarks |
| 9:00AM - 9:45AM | Bayesian Materials Discovery
Prof. Raymundo Arróyave, Materials Science & Engineering |
| 9:45AM - 10:30AM | Guided Deep Learning Manifold Linearization of Porous Media Flow Equations
Prof. Eduardo Gildin, Petroleum Engineering |
| 10:30AM - 10:50AM | Coffee Break Sponsored by Dell Technologies |
| 10:50AM - 11:00AM | Opening Remarks
Prof. Brendan Roark Associate Vice President For Research, Centers and Institutes, Office of the Vice President for Research |
| 11:00AM - 12:00PM |
Keynote: Tuberculosis Drug Discovery - application of computational approaches in a unique industry/academic collaboration (pdf)
Dr. Steven J. Berthel, Tuberculosis Drug Accelerator (TBDA) Program Manager and Lead Medicinal Chemist. Panorama Global, Seattle WA |
| 12:00PM - 1:00PM | Lunch Sponsored by NVIDIA |
| 1:00PM - 1:30PM | GPU Accelerated Molecular Docking
Dr. Greg Zynda, NVIDIA Sr. Solution Architect |
| 1:30PM - 2:00PM | Molecular Dynamics Simulations in Designing Novel Peptide-based Cancer Drug Nanocarriers
Prof. Phanourios Tamamis, Chemical Engineering |
| 2:00PM - 2:30PM | In silico characterization of drugs with potential protein target inhibition against Trypanosoma cruzi and Leishmania major
Prof. Sol Milena Mejia Chica, Chemistry, Javeriana University |
| 2:30PM - 2:50PM | Coffee Break Sponsored by Summus Industries |
| 2:50PM - 3:35PM | RAPIDS: GPU Accelerated Data Science
Dr. Srivathsan Koundinyan, NVIDIA Software Architect |
| 3:35PM - 4:05PM | Efficient Lossy Compression of High-Resolution Scientific Data with Autoencoder
Prof. Jian Tao, School of Performance, Visualization & Fine Arts |
| 4:05PM - 5:00PM | Open Session/Poster Setup |
| 5:00PM - 7:00PM | Banquet and Poster Session
ILSB Lobby map |
| Fri. May 19 | Keynote and Research Talks (ILCB Rm. 224 map) |
| 8:30AM - 9:15AM | Check-in |
| 9:15AM - 10:00AM | Lightning Talks
Tung Yan Liu, Why this way? An atomistic study on diffusion pathway in nanocomposite of immiscible metals Razeen Shaikh, Constraining the predictions of conserved SMAD signaling pathway through parameter identifiability informed experimental design. |
| 10:00AM - 10:30AM | Frontera, Stampede, and Lonestar at TACC: Compute resources for the scientific community (pdf)
Dr. Lars Koesterke, Texas Advanced Computing Center (TACC) |
| 10:30AM - 10:50AM | Coffee Break |
| 10:50AM - 11:00AM | Opening Remarks
Prof. Brendan Roark Associate Vice President For Research, Centers and Institutes, Office of the Vice President for Research |
| 11:00AM - 12:00PM |
Keynote: The Computing and Information Science and Engineering Landscape: A Look Forward
Dr. Margaret Martonosi, National Science Foundation’s (NSF) Assistant Director for Computer and information Science and Engineering (CISE) |
| 12:00PM - 1:00PM | Lunch Sponsored by DDN |
| 1:00PM - 2:00PM | Introduction to Quantum-Centric Supercomputing
Robert Loredo, IBM Quantum Ambassador |
| 2:00PM - 2:30PM | Accelerating Computing for Emerging Sciences (ACES): An Innovative Composable Hardware Platform for the Development of Transformative Scientific Workflows
Dr. Lisa Perez, High Performance Research Computing |
| 2:30PM - 2:50PM | Coffee Break |
| 2:50PM - 3:10PM | Quantifying biological structure using light-sheet fluorescence microscopy and fluorescence tractography
Dr. Holly Gibbs, Microscopy & Imaging Center, Biomedical Engineering |
| 3:10PM - 4:00PM | Lightning Talks
Devon Joseph Boland, AlphaFold2: Integration Into an Undergraduate Curriculum Andrew J. Harris, Felid Phylogenomics in the Era of High Performance Research Computing Debasish Mishra, Global Scale Analysis of High Resolution Satellite Datasets |
Posters
Thanks to our Sponsors!
Texas A&M Research Computing Symposium is supported in part by NSF award #1925764, CC* Team: SWEETER -- SouthWest Expertise in Expanding, Training, Education and Research and NSF award #2112356, ACSS: ACES - Accelerating Computing for Emerging Sciences.