The International Conference for High Performance Computing, Networking, Storage, and Analytics, or “Supercomputing” (SC) for short, was held in Denver from November 12-17 and hosted nearly 14,000 attendees. SC is the premier event for advances in algorithms, applications, architectures and networks, clouds and distributed computing, data analytics and visualization, machine learning and HPC, programming systems, system software, and state of the practice in large-scale data storage, deployment and integration. Each year, SC provides a unique opportunity to meet leaders in the field of high-performance computing, including researchers at universities and government labs, and hardware vendors like Intel, AMD, NVIDIA, and Penguin Computing.
The theme for this year’s event was “I am HPC; Impact and Future Direction,” focusing on the ways in which HPC impacts society as well as the community of researchers in HPC. An interdisciplinary cohort comprised of Georgia Tech researchers from the Partnership for an Advanced Computing Environment, the Center for High-Performance Computing, the School of Computational Science and Engineering, the Center for Research into Novel Computing Hierarchies, the Institute for Data Engineering and Science, and the School of Computer Science at various levels of their career were in attendance to present technical talks, participate in workshops and promote HPC research at Georgia Tech with a booth in the exhibit hall.
Georgia Tech teams were well represented across the research themes, including presentations on; large graph analytics, new methods for high-performance data-intensive workloads, challenges presented by the exascale computing, and Large Language Models (LLMs) applications in codesign. Jeffrey Young and Richard Vuduc were feature speakers in the tutorial “Leveraging SmartNICs for HPC Applications” that offered attendees an in-depth exploration of the state-of-the-art for SmartNICs and the emerging software ecosystems supporting them. Georgia Tech was also represented in the Birds of a Feather Co-Hort Panel Discussions on “Software Testing for Scientific Computing in HPC” and “Scientific Software and the People Who Make It Happen: Building Communities of Practice”. Of special mention is the Special Topic Workshop on “Machine Learning with Graphs in High Performance Computing Environments” organized by Richard Vuduc of Georgia Tech as well as Seung-Hwan Lim, Catherine Schuman, and Jose Moreira.
Georgia Tech researchers had numerous discussions with potential collaborators and new partners for initiatives in high performance computing, including conference attendees from universities, government labs, and industry. The team also had a great opportunity to reconnect with numerous alumni, who stopped by the GT booth to tell us about their careers since graduation. Georgia Tech graduates are doing some amazing things in computing hardware, algorithms, and software, with applications across a wide range of engineering and science problems.
The goals of the funded proposals include identifying prominent emerging research directions on the topic of AI, shaping IDEaS future strategy in the initiative area, building an inclusive and active community of Georgia Tech researchers in the field that potentially include external collaborators, and identifying and preparing groundwork for competing in large-scale grant opportunities in AI and its use in other research fields.
Overview: The goal of this initiative is to bring together expertise in machine learning/AI, high-throughput computing, computational chemistry, and experimental materials synthesis and characterization to accelerate material discovery. Computational chemistry and materials simulations are critical for developing new materials and understanding their behavior and performance, as well as aiding in experimental synthesis and characterization. Machine learning and AI play a pivotal role in accelerating material discovery through data-driven surrogate models, as well as high-throughput and automated synthesis and characterization.
Overview: Zhigang Jiang is currently leading an initiative within IMAT entitled “Quantum responses of topological and magnetic matter” to nurture multi-PI projects. By crosscutting the IMAT initiative with this IDEAS call, we propose to support and feature the applications of AI on predictive and inverse problems in quantum materials. Understanding the limit and capabilities of AI methodologies is a huge barrier of entry for Physics students, because researchers in that field already need heavy training in quantum mechanics, low-temperature physics and chemical synthesis. Our most pressing need is for our AI inclined quantum materials students to find a broader community to engage with and learn. This is the primary problem we aim to solve with this initiative.
Overview: Our objective is to use large language models (LLMs) in conjunction with AI algorithms to identify effective driver proteins, develop screening algorithms that target appropriate binding sites while avoiding deleterious ones, and consider bioavailability and drug resistance factors. LLMs can rapidly analyze vast amounts of information from literature and bioinformatics tools, generating hypotheses and suggesting molecular modifications. By bridging multiple disciplines such as biology, chemistry, and pharmacology, LLMs can provide valuable insights from diverse sources, assisting researchers in making informed decisions. Our aim is to establish a first-in-class, LLM driven research initiative at Georgia Tech that focuses on designing highly effective small molecule libraries to treat challenging diseases. This initiative will go beyond existing AI approaches to molecule generation, which often only consider simple properties like hydrogen bonding or rely on a limited set of proteins to train the LLM and therefore lack generalizability. As a result, this initiative is expected to consistently produce safe and effective disease-specific molecules.
Overview: We are committed to building a team of interdisciplinary & transdisciplinary researchers and practitioners with a shared goal: developing a new framework which model future climatic variations and the interconnected and interdependent energy infrastructure network as complex systems. To achieve this, we will harness the power of cutting-edge climate model outputs, sourced from the Coupled Model Intercomparison Project (CMIP), and integrate approaches from Machine Learning and Deep Learning models. This strategic amalgamation of data and techniques will enable us to gain profound insights into the intricate web of future climate-change-induced extreme weather conditions and their immediate and long-term ramifications on energy infrastructure networks. The seed grant from IDEaS stands as the crucial catalyst for kick-starting this ambitious endeavor. It will empower us to form a collaborative and inclusive community of GT researchers hailing from various domains, including City and Regional Planning, Earth and Atmospheric Science, Computer Science and Electrical Engineering, Civil and Environmental Engineering etc. By drawing upon the wealth of expertise and perspectives from these diverse fields, we aim to foster an environment where innovative ideas and solutions can flourish. In addition to our internal team, we also have plans to collaborate with external partners, including the World Bank, the Stanford Doerr School of Sustainability, and the Berkeley AI Research Initiative, who share our vision of addressing the complex challenges at the intersection of climate and energy infrastructure.
Overview: Our research team envisions a significant trend in the exploration of AI applications for urban flooding hazard forecasting. Georgia Tech possesses a wealth of interdisciplinary expertise, positioning us to make a pioneering contribution to this burgeoning field. We aim to harness the combined strengths of Georgia Tech's experts in civil and environmental engineering, atmospheric and climate science, and data science to chart new territory in this emerging trend. Furthermore, we envision the potential extension of our research efforts towards the development of a real-time hazard forecasting application. This application would incorporate adaptation and mitigation strategies in collaboration with local government agencies, emergency management departments, and researchers in computer engineering and social science studies. Such a holistic approach would address the multifaceted challenges posed by urban flooding. To the best of our knowledge, Georgia Tech currently lacks a dedicated team focused on the fusion of AI and climate/flood research, making this initiative even more pioneering and impactful.
Overview: Most asset management and recycling use technology that has not changed for decades. The use of bar codes and RFID has provided some benefits, such as for retail returns management. Automated sorting of recyclables using magnets, eddy currents, and laser plastics identification has improved municipal recycling. Yet the overall field has been challenged by not-quite-easy-enough identification of products in use or at end of life. AI approaches, including computer vision, data fusion, and machine learning provide the additional capability to make asset management and product recycling easy enough to be nearly autonomous. Georgia Tech is well suited to lead in the development of this application. With its strength in machine learning, robotics, sustainable business, supply chains and logistics, and technology commercialization, Georgia Tech has the multi-disciplinary capability to make this concept a reality, in research and in commercial application.
Overview: Artistic human movement at large, stands at the precipice of a data-driven renaissance. By leveraging novel tools, we can usher in a transparent, data-driven, and accessible training environment. The potential ramifications extend beyond dance. As sports analytics have reshaped our understanding of athletic prowess, a similar approach to dance could redefine our comprehension of human movement, with implications spanning healthcare, construction, rehabilitation, and active aging. Georgia Tech, with its prowess in AI, HCI, and biomechanics is primed to lead this exploration. To actualize this vision, we propose the following research questions with ballet as a prime example of one of the most complex types of artistic movements: 1) What kinds of data - real-time kinematic, kinetic, biomechanical, etc. captured through accessible off-the-shelf technologies, are essential for effective AI assessment in ballet education for young adults?; 2) How can we design and develop an end-to-end ML architecture that assesses artistic and technical performance?; 3) What feedback elements (combination of timing, communication mode, feedback nature, polarity, visualization) are most effective for AI- based dance assessment?; and 4) How does AI-assisted feedback enhance physical wellness, artistic performance, and the learning process in young athletes compared to traditional methods?
Proposed Workshop: “Foundation of scientific AI (Artificial Intelligence) for Optimization of Complex Systems”
Primary PI: Peng Chen, Assistant Professor, School of Computational Science and Engineering
Proposed Series: “Guest Lecture Seminar Series on Generative Art and Music”
Primary PI: Gil Weinberg, Professor, School of Music
Title: Human-in-the-Loop Musical Audio Source Separation
Topics: Music Informatics, Machine Learning
Primary PI: Alexander Lerch, Associate Professor, School of Music
Co-PIs: Karn Watcharasupat, Music Informatics Group | Yiwei Ding, Music Informatics Group | Pavan Seshadri, Music Informatics Group
Title: Towards A Multi-Species, Multi-Region Foundation Model for Neuroscience
Topics: Data-Centric AI, Neuroscience
Primary PI: Eva Dyer, Assistant Professor, Biomedical Engineering
Title: Multi-point Optimization for Building Sustainable Deep Learning Infrastructure
Topics: Energy Efficient Computing, Deep Learning, AI Systems OPtimization
Primary PI: Divya Mahajan, Assistant Professor, School of Electrical and Computer Engineering, School of Computer Science
Title: Neutrons for Precision Tests of the Standard Model
Topics: Nuclear/Particle Physics, Computational Physics
Primary PI: Aaron Jezghani - OIT-PACE
Title: Continual Pretraining for Egocentric Video
Primary PI: : Zsolt Kira, Assistant Professor, School of Interactive Computing
Co-PI: Shaunak Halbe, Ph.D. Student, Machine Learning
Title: Training More Trustworthy LLMs for Scientific Discovery via Debating and Tool Use
Topics: Trustworthy AI, Large-Language Models, Multi-Agent Systems, AI Optimization
Primary PIs: Chao Zhang, School of Computational Science and Engineering & Bo Dai, College of Computing
Title: Scaling up Foundation AI-based Protein Function Prediction with IDEaS Cyberinfrastructure
Topics: AI, Biology
Primary PI: Yunan Luo, Assistant Professor, School of Computational Science and Engineering
Neurosciences research holds enormous potential for wide-ranging health and societal impact, and Georgia Tech's culture of applied research and integrated interdisciplinary liberal arts scholarship is uniquely positioned to create the environment in which Neuro Next can become an international leader in the discovery, innovation, and translation in neuroscience and neurotechnology.
Guided by faculty members Christopher Rozell, professor and Julian T. Hightower Chair in the School of Electrical and Computer Engineering; Simon Sponberg, Dunn Family Associate Professor of Physics and Biological Sciences; and Jennifer S. Singh, associate professor in the School of History and Sociology, the Neuro Next Initiative at Georgia Tech will lead the development of a community that supports collaborative research, unique educational initiatives, and public engagement in this critical field.
“Georgia Tech has a very strong, but decentralized, neuroscience community,” said Sponberg. “The Neuro Next Initiative really sprung from a lot of thoughtful input from dozens of people across many schools, colleges, and roles, which reflects how neuro interfaces so broadly. Our goal with this initiative is really to open a new front door to the neuro community here, to highlight the leadership that Georgia Tech is already taking in many areas of neuro-related research, and to create new ways to support our interdisciplinary work.” Aiming to foster a broad community that is passionate about shaping the frontiers of neuroscience and neurotechnology to better serve humanity, the initiative will launch in October.
“Neuroscience and neurotechnology have advanced dramatically in the last few years, making it clear that there are few endeavors that have as much potential societal impact as our study of the brain,” Rozell said. “Georgia Tech is uniquely positioned to build on its existing strengths to create an effort tailored to meet the scientific, technical, and social needs of these promising research trajectories. I'm excited that the Neuro Next Initiative represents the next step in creating that collaborative community.” By bringing together a cohort of faculty experts from varied disciplines, members aim to create a holistic and integrative approach to neuroscience and neurotechnology that centers real human impact and broad accessibility.
Singh noted, “Neuro Next is an important and exciting initiative that is prioritizing the inclusion of a range disciplinary expertise, including social science, humanities, business, and the arts, to critically investigate how we can research and develop neurotechnologies that are accessible, responsible, and socially just. Building a collaborative neurocommunity that centers societal impacts from the start shares the commitment of Georgia Tech to developing leaders who advance technology and improve the human condition.”
Numerous 2022-2023 research findings at Georgia Tech were supported by the NSF-MRI Hive HPC cluster and storage for data-driven discovery, an IDEaS Core Shared Facility. One major project with great local impact was the use of the HIVE to create epidemiological modeling of the COVID -19 outbreak for the State of Georgia. Other finding of note supported by HIVE include advancements in astrophysics related to gravitational waves, intermediate-mass black holes, and the evolution of the universe. Chemistry research results supported include the development simulation created datasets to train Machine Learning models for crystals, hydrogenation catalysis, and negative thermal expansion. The HIVE infrastructure also led to new data-driven analysis & prediction of process-structure-property linkages for rapid new materials discovery.
IDEaS continued to lead in the Data Science world in 2022-2023 as a founding member of the Academic Data Science Alliance (ADSA) and b providing expert voices at U.S. Data Science Leadership Summits. Additionally, IDEaS manages Georgia Tech data science relationships with DOE labs and serves as the lead university in the National Coordination Committee of the Big Data Hubs.
Strategic planning for the 2023-2024 period focused on the rise of AI in government funding decisions and the historical support provided by IDEaS in this area. Specific brainstorming sessions included AI-driven Research in Science and Engineering, Cyberinfrastructure for AI, and Engaging with Industry in the AI Era. Discussions covered ways best pursue future funding and provide support in this area of growing importance for the holistic benefit of Georgia Tech’s different units.
With about 200 affiliate faculty across all six colleges and GTRI, IDEaS is one of the 10 Interdisciplinary Research Institutions under the Georgia Tech EVPR/VPIR. The mission of IDEaS is to support basic and applied research, facilities, training, thought leadership, and external engagement in data science foundations and data driven discovery across disciplines. Learn more at our website.
- Christa M. Ernst
]]>1. What is your field of expertise and what questions, or challenges sparked your current research?
My expertise is in quantum chemistry, which is the application of quantum mechanics to problems in chemistry. I had the great fortune to participate in a summer research program in this area as an undergraduate, and I loved its intersection of physics, chemistry, math, and computer simulation. I am especially interested in interactions between molecules, which is relevant for solvation, crystal structures, biomolecular structure, and drug binding. It is an area that is surprisingly hard to model, and requires high-level quantum chemistry techniques.
2. How does the field of Data Science and Engineering intersect with/impact/enhance your research?
I specialize in generating large datasets that can be used to parameterize or test approximate models. The advent of modern machine-learning methods has allowed my group to develop very fast models of intermolecular interactions that are tremendously faster than the quantum chemistry computations that would otherwise be required to achieve a similar accuracy.
3. Why is the field of Data Science and Engineering important to the development of Georgia Tech’s broader research strategy?
Data science, machine learning, and high performance computing have enabled breakthroughs in numerous difficult research areas. They are becoming ubiquitous components of 21st century research.
4. What are the global and social benefits of the research you and your team conduct?
Our work on machine learning models of intermolecular interactions is being used by pharmaceutical companies for improved modeling of drug binding, which will hopefully help speed up the drug discovery process.
5. What are your plans on engaging a wider GT faculty pool with IDEaS research?
Georgia Tech has a strong collaborative spirit, and many faculty in science and engineering whose research would benefit from the latest advances in data science and high performance computing. At the same time, many of those advances are being created by GT researchers in computing. Through IDEaS, I hope to connect more of these researchers and to foster new collaborative efforts.
]]>The theme for this year’s event was “HPC accelerates,” focusing on the ways in which discovery in science and engineering is accelerated by high performance computing. An interdisciplinary cohort comprised of Georgia Tech researchers from the Partnership for an Advanced Computing Environment, the Center for High-Performance Computing, the School of Computational Science and Engineering, the Center for Research into Novel Computing Hierarchies, the Institute for Data Engineering and Science, and the School of Computer Science at various levels of their career were in attendance to present technical talks, participate in workshops and promote HPC research at Georgia Tech with a booth in the exhibit hall.
Georgia Tech teams were well represented across the research themes, including presentations on; standardization practices, software engineering, exascale computing, data graphing, and a novel simulator toolkit for co-design. Of special mention is the AMC Gordon Bell Finalist Paper, “Exaflops Biomedical Knowledge Graph Analytics” by Georgia Tech authors Richard Vuduc and Vijay Thakkar.* Georgia Tech faculty were involved in numerous workshops at SC22, including HCP training and education, implementing algorithms on graphics processing units (GPUs), and presenting better tools for developing parallel programs.
Faculty and students from Georgia Tech were integral in the success of Supercomputing 2022, providing planning advice for the organizing committees on Algorithms (Srinivas Aluru), Applications (Umit V. Catalyurek), Architecture and Networks (Tushar Krishna), Data Analytics, Visualization and Storage (Greg Eisenhauer), Machine Learning and HPC (Ramakrishnan Kannan), Post-Moore Computing (Richard Vuduc), Early Career Programs, Student Cluster Competition, and the Student Educational Competitions (Aroua Gharbi).
Georgia Tech researchers had numerous discussions with potential collaborators and new partners for initiatives in high performance computing, including conference attendees from universities, government labs, and industry. The team also had a great opportunity to reconnect with numerous alumni, who stopped by the GT booth to tell us about their careers since graduation. Georgia Tech graduates are doing some amazing things in computing hardware, algorithms, and software, with applications across a wide range of engineering and science problems.
-Christa M. Ernst
*Ramakrishnan Kannan, Piyush Sao, Hao Lu, Jakub Kurzak, Gundolf Schenk, Yongmei Shi, Seung-Hwan Lim, Sharat Israni, Vijay Thakkar, Guojing Cong, Robert Patton, Sergio E. Baranzini, Richard Vuduc, and Thomas Potok. 2022. Exaflops biomedical knowledge graph analytics. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC '22). IEEE Press, Article 6, 1–11.
]]>The four winning teams, led by PIs from across Georgia Tech’s Colleges and Schools, will host their workshops during the Spring 2023 semester at the Georgia Institute of Technology’s Atlanta campus.
Integrative Genomics for Health Equity
This one-day workshop will address the computational and analytical limitations to the use of integrative genomics and multi-omic profiling to understand and promote health equity. As genomic analysis begins to transform healthcare delivery, by promoting personalized assessment of therapeutic intervention, it is becoming increasingly apparent that both social and genetic determinants of health need to be measured. Equitable implementation of genomic medicine must evaluate the influences of ancestry as well as socioeconomic status alongside genetics, with effects mediated in part through gene expression and epigenetics. This workshop will bring together up to 9 speakers who will be asked to present their views on how genomic and non-genomic data can be integrated to guide precision medicine of diverse human populations.
Single Cell Spatial Omics
The field of single cell spatial omics is growing fast, thanks to global consortia such as the Human Cell Atlas (HCA) and the Human Biomolecular Atlas Program (HuBMAP), and also due to reduced next-generation sequencing (NGS) costs. Arguably, the biggest challenge in realizing the full potential of “spatial omics” techniques is the need for analytical tools that maximize our ability to extract testable hypotheses from the rich but noisy data sets. Thus, the AWSOM ’23 workshop will seek to bring together Atlanta-area strengths in computational science and machine learning at the same forum as technology developers and biologists, to strategically determine the thrust areas for future research.
Computational and Mathematical Approaches to Theoretical Neuroscience
Understanding how the human brain works is one of the major challenges of our times. There has been a lot of progress on modeling phenomena at micro scale, such as the model of a neuron, of the chemical channels in a Synapse, learning models for updating weights in neurons etc. Such models have also inspired the models behind modern deep learning architectures. Rapid developments in neuro imaging at both micro and macro levels has enabled us to look at brain phenomena at unprecedented scale. However, an overarching model that explains the macro behavior of the brain is still not found. There have been several exciting steps towards this direction in the last decade from researchers at the intersection of several fields including computational neuroscience, theoretical CS, and probability. The focus of this seminar series is to invite researchers in this space to Georgia Tech, so that students and faculty at GT can pick up and contribute to this young and emerging field.
Sunny Workshop: A Julia Package for The Modeling of Spin Dynamics in Quantum Materials
In recent years, working with scientists at the University of Tennessee and Los Alamos National Laboratory (LANL), we have developed a simulation package called Su(n)ny, that uses Monte- Carlo techniques to calculate the spin dynamics of systems of interests. The Su(n)ny package is written in Julia and currently hosted on Github: https://github.com/SunnySuite/Sunny.jl. Development took place in the last year and a half. Last month, we presented our work for the first time during a workshop at Oak Ridge National Laboratory, as well as tutorials on how to use this package: https://github.com/SunnySuite/SunnyTutorials/tree/main/tutorials, see also the introductory video here: https://mourigal.gatech.edu/public/Sunny-Install-Video-Mourigal.mp4 The package was very well received by our community, and it is now time to accelerate its deployment in realistic community use cases, by coupling it to the modeling of real data, porting it on GPU/Leadership class computers, advertising it more broadly, and including AI/ML methodologies to extract models from data. Learn About the Package Here https://docs.juliahub.com/Sunny/atBCQ/0.3.0/
IDEaS leverages expertise and resources from throughout Georgia Tech's colleges, research labs, and external partners, to define and pursue grand challenges in data science foundations and in data-driven discovery in various fields. For updates on these workshops and other IDEaS events, please visit our website
- Christa M. Ernst
]]>