Fifth Annual Texas A&M Research Computing Symposium

Last Update: May 15, 2022

Symposium Details

Dates: May 23-26, 2022
Location: ILCB 224 & 233 (map)
Questions? Call us at (979) 458-8414 or email help@hprc.tamu.edu

Symposium Registration
Workshop Details & Registration

Texas A&M's High Performance Research Computing is hosting a series of talks and workshops May 23-26, 2022 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 during lightening talks or the poster session.

Check back regulary for updated details on Keynote presentations, talks, and Workshops!

Keynote Talks

Monday May 23, 2022

Accelerating Computing for Transforming Convergence and Geospatial Sciences

Shaowen Wang, Ph.D., Professor and Head of the Department of Geography and Geographic Information Science, University of Illinois Urbana-Champaign (UIUC)



Abstract: Geospatial discovery and innovation have been undergoing an extreme digital transformation enabled by artificial intelligence and cyberGIS during the past decade. This transformational trend seems likely to persist into the foreseeable future. Meanwhile cyberGIS has emerged as a new generation of geographic information science and systems (GIS) based on holistic integration of high-performance and distributed computing, data-driven knowledge discovery, visualization and visual analytics, and collaborative problem-solving capabilities. This presentation discusses challenges and opportunities for advancing convergence and geospatial sciences to tackle an array of pressing sustainability and resilience challenges through cyberGIS-enabled holistic computing approaches.

Bio: Shaowen Wang is Professor and Head of the Department of Geography and Geographic Information Science; and Affiliate Professor of the Department of Computer Science, Department of Urban and Regional Planning, and School of Information Sciences at the University of Illinois Urbana-Champaign (UIUC). He has served as Founding Director of the CyberGIS Center for Advanced Digital and Spatial Studies at UIUC since 2013. He served as Associate Director of the National Center for Supercomputing Applications for CyberGIS from 2010 to 2017. His research interests include geographic information science and systems (GIS), advanced cyberinfrastructure and cyberGIS, complex social and environmental problems, computational and data sciences, geospatial science and technology, high-performance and distributed computing, and spatial analysis and modeling. He has received research funding from several U.S. federal and state agencies (e.g., CDC, DOE, Illinois EPA, NASA, NIH, NSF, USDA, and USGS) and industry, and served as the Principal Investigator (PI) of more than $30 million competitive research grants. He currently serves as the PI and Director of the NSF Institute for Geospatial Understanding through an Integrative Discovery Environment (I-GUIDE). He has published over 160 peer-reviewed papers and edited or co-edited several books and proceedings. He has served as an action editor of GeoInformatica, associate editor of SoftwareX, and guest editor or editorial board member for multiple other journals, book series, and proceedings. He received the NSF CAREER Award in 2009. He was named a Helen Corley Petit Scholar for 2011-2012, Centennial Scholar for 2013-2016, and Richard and Margaret Romano Professorial Scholar for 2018-2021 by UIUC’s College of Liberal Arts and Sciences. He is a Fellow of the American Association for the Advancement of Science (AAAS) and Fellow of the American Association of Geographers (AAG). He received the 2022 AAG Distinguished Scholarship Honors. He served as President of the University Consortium for Geographic Information Science from 2016 to 2017, and as a member of the Board on Earth Sciences and Resources of the National Academies of Sciences, Engineering, and Medicine from 2015 to 2020. He has supervised more than 30 PhD students and postdoctoral fellows, and many of his advisees are holding positions at major research universities, premier research and development laboratories, and leading geospatial companies.



Tuesday May 24, 2022

Democratizing Science through Advanced Cyberinfrastructure

Manish Parashar, Ph.D., Office Director, Office of Advanced Cyberinfrastructure (OAC), National Science Foundation



Abstract: Science and engineering (S&E) research is being transformed by the increasing availability and scales of computation and data and the national cyberinfrastructure (CI) ecosystem has become a key catalyst for discovery and innovation. It is thus imperative, now more than ever that all researchers can equally benefit from the opportunities for scientific exploration enabled by computation and data. In this talk I will discuss NSF’s vision for a national CI ecosystem that ensures broad, fair, and equitable access to advanced resources, services, and expertise. Such a CI ecosystem can drive new thinking and enable transformative discoveries for all, democratizing science in the 21st century

Bio: Manish Parashar is Office Director of the Office of Advanced Cyberinfrastructure at the National Science Foundation (NSF) where he oversees investments in national cyberinfrastructure. He also serves as Co-Chair of the National Science and Technology Council’s Subcommittee on the Future Advanced Computing Ecosystem and the National Artificial Intelligence Research Resource Task Force. Manish is on assignment to NSF from the University of Utah where he is the Director of the Scientific Computing and Imaging Institute, Chair in Computational Science and Engineering, and Professor in the School of Computing. Manish is Fellow of AAAS, ACM, and IEEE. For more information, please visit http://manishparashar.org.




Workshops

Workshop Registration

Introduction to AlphaFold for 3D Protein Structure Prediction on Grace

Wednesday, May 25 9:30AM - 12:00PM

HPRC is offering a 2 1/2-hour workshop on Alphafold for 3D protein structure prediction on Grace. In this workshop, participants will learn about how to run AlphaFold on Grace, HPRC's flagship system and the fundamentals of Alphafold as applied to real world applications.
Prerequisites: HPRC account on Grace

Topics will include:
  • Introduction to AlphaFold
  • Running AlphaFold on Grace
  • AlphaFold Workflows
  • Visualizing AlphaFold results

Implementing AI/ML Workloads on Graphcore's IPU based system

Wednesday, May 25 9:00AM - 1:00PM

Graphcore is hosting a 4-hour workshop on implementing AI/ML workloads on Graphcore's IPU based systems which will be a component of HPRC's NSF funded FASTER and upcoming ACES systems. Participants will be guided through hands-on exercises by Graphcore specialist.
Prerequisites: High level understanding of AI/ML concepts and frameworks

Topics will include:
    Introduction to Graphcore, IPU, and Poplar
    Frameworks on IPU
    • TensorFlow1 - TF1 porting examples, using on-device loops and infeeds, half- and mixed-precision, model-parallel
    • TensorFlow2 & Keras - porting examples and optimization, mixed-precision, replication, model-parallel, and custom training loops
    • PyTorch - PopTorch example, DataLoader, options to optimize performance, efficient data loading, observing tensors, and fine-tuning BERT
    Debugging and profiling - adding instrumentation, creating profiles, analyzing with PopVision tools Research directions on the IPU (12-1PM)

Intel OneAPI AI Analytic Toolkit

Wednesday, May 25 1:00PM - 5:00PM

Intel is hosting a 4-hour workshop on Intel's OneAPI AI Analytic Toolkit and the performance benefits achieved on intel XPUs (CPUs, GPUs) from using the Intel optimizations. This workshop will be presented by Intel engineers. Participants will receive a certificate of completion from Intel. HPRC's upcoming NSF funded ACES system will include Intel CPUs and GPUs.

The workshop will cover Intel optimizations implemented on top of stock versions of data science libraries like NumPy, SciPy, Scikit Learn, and DL frameworks like Tensorflow and Pytorch. Hands on exercises will be followed to showcase how to get started using Intel OneAPI AI Analytic Toolkit software and the performance benefits achieved from using Intel optimizations.
Prerequisites: High level understanding of AI/ML concepts and frameworks. Please see specific Skill Level requirements as listed in the agenda.

Agenda:
    Lecture - What is OneAPI - AI Analytics Toolkit
    Intel Distribution for Python (IDP)
    • Skill Level – High level understanding of some data science Python libraries, Python beginner level
    • Overview of optimizations inside Python
    • Exercise https://github.com/mtolubaeva/numpy-tests
    • Expected Outcome be able to see the performance benefit of using IDP libraries over stock Python libraries like NumPy, SciPy etc.
    Intel Extensions for Scikit Learn Intel Optimization for PyTorch
    • Skill Level – High level understanding of Deep Learning concepts, Pytorch beginner level
    • Overview types of optimizations, PyTorch
    • Exercise https://github.com/jingxu10/retinanet_ipex
    • Expected Outcome be able to see the performance benefit of using Intel Optimizations for Pytorch over stock Pytorch framework.
    Intel Optimizations for TensorFlow

Full Schedule (All times are CDT)

Last Update: May 15, 2022

Monday, May 23 Keynote and Research Talks (ILCB Rm. 224 map)
8:20AM - 8:50AM Check-in
8:50AM - 9:00AM Welcoming Remarks
9:00AM - 9:45AM Flames, Fire Tornadoes, and the Blue Whirl … What More Can There Be? — Multi-scale numerical simulations now show the way.
Prof. Elaine Oran, Aerospace Engineering
Member of the National Academy of Engineering
9:45AM - 10:15AM Theory/computation role in tuning surface/electrolyte interfaces for enhancing catalytic performance
Prof. Perla Balbuena, Chemical Engineering
10:15AM - 10:30AM Break
10:30AM - 10:40AM Opening Remarks:
Prof. Jack Baldauf
Interim Vice President for Research, Texas A&M University Division of Research
10:40AM - 11:40AM Keynote: Accelerating Computing for Transforming Convergence and Geospatial Sciences
Prof. Shaowen Wang
Professor and Head of the Department of Geography and Geographic Information Science, University of Illinois Urbana-Champaign (UIUC)
11:40AM - 1:00PM Lunch
1:00PM - 1:30PM Machine Learning for Atmospheric Modeling
Prof. Istvan Szunyogh, Atmospheric Sciences
1:30PM - 2:00PM A Geospatial Cyberinfrastructure for Convergence Science
Prof. Zhe Zhang, Geography
2:00PM - 2:30PM Data-Driven Methods for Accelerating Vibrational Spectroscopy Modeling at the Medium to Large Scale
Prof. Daniel Tabor, Chemistry
2:30PM - 2:50PM Break
2:50PM - 3:20PM Beyond Graphite for Li-ion Batteries: Searching for Lithium Metal Alternatives Using Quantum Mechanical
Prof. Jorge Seminario, Chemical Engineering
3:20PM - 3:50PM Making Scientific Discoveries with Scientific Machine Learning
Dr. Ming Zhong, Texas A&M Institute of Data Science
Open Session/Poster Setup
5:00PM - 7:00PM Banquet and Poster Session Sponsored by Liqid
Tuesday, May 24 Keynote and Research Talks (ILCB Rm. 224 map)
8:20AM - 8:45AM Check-in
8:45AM - 9:00AM Opening Remarks:
Prof. Costas Georghiades
Senior Associate Vice President for Research, Texas A&M University Division of Research
9:00AM - 10:00AM Keynote: Democratizing Science through Advanced Cyberinfrastructure
Dr. Manish Parashar
Office Director, Office of Advanced Cyberinfrastructure (OAC), National Science Foundation
10:00AM - 10:30AM Morning Talks
10:30AM - 10:45AM Break
10:45AM - 11:15AM
Adaptive Bayesian Sum of Trees Model for Covariate Dependent Spectral Analysis
Prof. Scott Bruce, Statistics
10:15AM - 11:45AM
Modes of Motions of a Coronavirus
Prof. Goong Chen, Math
11:45AM-1:00PM Lunch Sponspored by NVIDIA
1:00PM - 1:50PM Accelerating the secondary analysis of next generation sequencing data with NVIDIA Parabricks
Dr. Greg Zynda, NVIDIA Senior Solutions Architect
1:50PM - 2:30PM End-to-End Optimization of AlphaFold2 on Intel Architecture
Dr. Luke Ge, Intel AI Technical Solution Specialist
2:30PM - 2:50PM Break
2:50PM - 3:30PM How learning physical laws can help the energy industry
Dr. Nefeli Moridis, NVIDIA Developer Relationship Manager for Subsurface, Global Energy Team
3:30PM - 4:00PM Recombination-aware phylogenomics in mammals
Dr. Nicole Foley, Veterinary Integrative Biosciences
4:00PM - 5:00PM Open Session
Wednesday, May 25 Workshops (ILCB Rm. 224 & 233 map)
9:30 AM - 12:00 PM Introduction to AlphaFold for 3D Protein Structure Prediction on Grace
Dr. Michael Dickens and Devon Boland
9:00AM - 1:00 PM Graphcore: Implementing AI/ML workloads on Graphcore's IPU based system
Dr. Alexander Tsyplikhin and Dr. Mario Krell, Graphcore
1:00PM - 5:00PM Intel OneAPI AI Analytic Toolkit
Louie Tsai, Intel Artificial Intelligence Consultant
Thursday, May 26 Special Events
SWEETER Annual Meeting

Thanks to our Sponsors!

Symposium 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.