Guided Interest Groups (GIGs) are interactive, community-driven learning experiences designed to help students make the most of the SC Technical Program while connecting with peers who share their interests.
Whether you’re new to high performance computing or eager to explore the latest advances, there’s a GIG for you. This year’s groups cover a diverse range of topics, from HPC fundamentals and emerging technologies to artificial intelligence, machine learning, sustainability, and scientific applications.
GIGs Kickoff
Sunday, 15 Nov 2026
Time TBD
See sessions below for details.
Student Volunteers ChairSuzanne Prentice, Oak Ridge National Laboratory (ORNL)
Guided Interest Groups Chair
Shivangi Gupta, Macon & Joan Brock Virginia Health Sciences at Old Dominion University
Find Your GIG. Meet Your People. Explore SC.
GIGs are open to all students attending SC, with priority given to students participating in the Students@SC cohorts.
Each GIG kicks off with a dedicated event where you’ll meet your group, connect with your GIG leaders, and start exploring the SC Technical Program together.
Pre-registration is required to attend the GIG Kickoff.
Choose your area of interest and sign up below (beginning Oct 9).
9 OCT 2026
Sign-ups Open
6 NOV 2026
Sign-ups Close
15 NOV 2026
Pre-registration is required to attend the GIG kickoff. Choose your area of interest and sign up!
Please note that the current schedule is tentative, and a more finalized schedule will be posted at the end of the month. In the meantime, please sign up based on your area of interest.
As scientific research tackles bigger and more complex challenges, high-performance computing (HPC) has become an essential tool for solving them. This GiG will showcase how researchers use some of the world’s most powerful supercomputers to solve real-world engineering and scientific problems. Students will learn about the latest advances in HPC, discover how these systems support groundbreaking research, and see the impact of computing across a wide range of fields.
Lorenzo Piarulli
Lorenzo is a first-year PhD student in Computer Science at Sapienza University of Rome, where he researches high-performance parallel algorithms for emerging accelerators. His current focus is on large-scale genomics algorithms, multi-accelerator computing, and benchmarking. He earned his M.Sc. in Computer Science from Sapienza University of Rome, focusing on stencil computations on dataflow architectures. Lorenzo also serves as the Invited Talks, Keynote, and Plenary Lead Student Volunteer for the SC26.
Jay Ashworth
Jay is a 3rd year Ph.D student in Computer Science from the University of Tennessee, Knoxville, where he is advised by Dr. Michela Taufer. His research interests include HPC job scheduling and performance analysis, and he is currently developing Flux Fiction, a HPC system emulator built on Flux in collaboration with Lawrence Livermore National Laboratory. He also earned his B.S. and M.S. in Computer Science at the University of Tennessee, where he was on a world championship-winning VEXU robotics team and began researching HPC. Jay is serving as Co-Lead SVOL for the Infrastructure and Wayfinding Committee at SC26.
Monday, 16 Nov
9 am–12:30 pm, W176b
Workshop: High-Performance Computing for Environmental and Earth Sciences (HPC4EES)
2–5:30 pm, W176c
Workshop: ExaMPI26: Workshop on Extreme Scale MPI
2–5:30 pm, W181b
Workshop: High-Accuracy Computing on Low-Precision Hardware
2–5:30 pm, W176a
Workshop: The 12th Computational Approaches for Cancer Workshop (CAFCW26)
Tuesday, 17 Nov
8:30–10 am, W375de
Keynote: Animashree Anandkumar
10:30 am–12 pm, W181abc
Paper: ACM Gordon Bell Finalist
1:30–3 pm, W181abc
Paper: ACM Gordon Bell Climate Modeling Finalist
Wednesday, 18 Nov
10:30 am–12 pm, W185abc
Panel: Medical Digital Twins: Can HPC Unite the Future for Health Globally?
10:30 am–12 pm, W175abc
Paper: Scalable Search and Data Analytics for Scientific Discovery
Thursday, 19 Nov
8:30–10 am, W179ab
Paper: Adapting Scientific Computing to AI-Oriented Accelerators
1:30–3 pm, W179ab
Paper: Reengineering Scientific Simulation for Modern Accelerators
High-performance computing (HPC) is often associated with powerful computers, advanced algorithms, and technical performance. However, behind every HPC system are people who build, use, and benefit from these technologies. This GIG will introduce students to sessions that explore not only the technical side of HPC, but also topics such as data, accessibility, ethics, and the real-world impact of computing. Students will gain a broader understanding of how HPC can be used to solve important challenges while making a positive difference for society.
Alex Kiefer
Alex is a second-year Ph.D. student in Data Science and Engineering at the Bredesen Center, where he researches artificial intelligence for spatio-temporal modeling. Alex earned his B.S. and M.S. in Computer Science from Indiana University, conducting research on graph neural networks and trustworthy human-AI interaction. He serves as the Lead Student Volunteer for the Posters and Doctoral Showcase at the SC26.
Rahat Zaman
Rahat is a fourth year Ph.D. student in Computer Science at the University of Utah. His research lies at the intersection of human-AI interaction, data visualization, and explainable AI, with a focus on designing interactive systems that support more transparent, interpretable, and steerable data analysis. His work explores how visual interfaces and human-centered approaches can help users better understand complex data and AI-driven processes, enabling more effective collaboration between people and intelligent systems.
Shadmaan Hye
Shadmaan is a fifth-year Ph.D. student in Computer Science at the Scientific Computing and Imaging (SCI) Institute at the University of Utah. Her research focuses on interactive data visualization for high-performance computing, with an emphasis on making complex system and performance data more interpretable. In collaboration with Lawrence Livermore National Laboratory (LLNL), her current work explores interactive approaches for analyzing and visualizing low-level assembly instructions in relation to their corresponding source code, helping bridge the gap between high-level programs and their execution on modern computing systems.
9 am–5:30 pm, W179b
Workshop: 8th Workshop on Programming and Performance Visualization Tools (ProTools)
9 am–5:30 pm, W179a
Workshop: 2nd Annual Workshop on Large-Scale Quantum-Classical Computing (LSQCC)
2–5:30 pm, W181c
Workshop: AI on HPC: Performance Engineering, Challenges and Opportunities
12:15–1:15 pm, W192b
BoF: Ethics in HPC: With Great Power comes Great Responsibility
12:15–1:15 pm, W183c
BoF: The Impact of GenAI on HPC Programming and Programming Models
5:15–6:45 pm, W194b
BoF: Who and What Is on Your Machine? Meeting the Coming Rules for Shared AI Compute Without Slowing the Science
3:30–5 pm, W184bcd
Panel: The Future of the HPC Workforce: Skills, Scale, and Sustainability
10:30 am–12 pm, W184bcd
Paper: My Coauthors Don’t Sleep: Agentic AI and Trust in Computational Science
12:15–1:15 pm, W190b
Paper: AI assisted engineering in HPC
As high-performance computing (HPC) systems become more powerful, they also require more energy to operate. This creates challenges related to cost, resource use, and environmental impact. In this GIG, students will explore how researchers are developing new ideas and technologies to make HPC more energy-efficient and sustainable while continuing to support important scientific discoveries.
Matheus Costa
Matheus is a Ph.D. student in Computer Science at the Federal University of Rio Grande do Sul (UFRGS), where he researches energy-efficient high-performance computing, GPU resource management, and power-aware execution of coupled HPC and artificial intelligence workflows. His work explores GPU sharing, dynamic frequency control, and workflow-aware runtime techniques to improve the performance and efficiency of scientific applications. He earned his B.S. in Computer Science from UFRGS in 2025. Matheus serves as the Digital Experience Lead Student Volunteer for the Students@SC program.
Naman Kulshreshtha
Naman is a fifth-year PhD student at Queen’s University, Canada, specializing in GPU resource and power management. His research focuses on GPU resource-sharing mechanisms and how to use them to improve overall system efficiency. He is also deeply interested in power-based scheduling for computing clusters. Currently, Naman is exploring resource partitioning in modern AMD GPUs and APUs to develop more efficient scheduling policies. Additionally, he will be serving as a Lead Student Volunteer for the Community Engagement Team at the Students@SC program.
2–5 pm
Workshop: Design, Energy and Workload Characterization
4:36–4:48 pm
Workshop Paper: A Comparative Study of Energy Scaling Behavior for AI Training: Wafer or Die Scale
5–5:12 pm
Workshop Paper: Watts Behind the Weights: Characterizing Energy Consumption of the AI Training Lifecycle in HPC
5:12–5:24 pm
Workshop Paper: Characterizing Simulation-AI Coupled Workflows on Frontier
10:52–11:15 am
Paper: EMO: Energy Efficiency Modeling and Optimization for AI Workloads
12:15–1:15 pm
BoF: HPC Procurement, Energy Efficiency and Sustainability
11:15–11:37 am
Paper: HolyDiver: Water and Carbon Footprint-Aware Serverless Computing
3:30–5 pm
Panel: Total Energy to Solution: The Computational and Economic Breakeven of Hybrid HPC/ML
10:30–10:52 am
Paper: PHANTOM: Phase-Aware Power Management for Energy-Efficient LLM Training
Paper: Scalable and Efficient Simulation of LLM Training
Paper: Cross-Layer Energy Analysis of Multimodal Training on Grace Hopper Superchips
12:15–1:15 am
BoF: Three Axes for Scientific AI on HPC: Energy Efficiency, Uncertainty, and Verifiable Trust
As artificial intelligence and machine learning continue to transform scientific research, it is essential to understand the algorithms, computing infrastructure, and computational methods that enable these advances at scale. This GIG explores the intersection of AI/ML and computational science, focusing on the development of efficient algorithms, scalable software and hardware infrastructure, and their application to solving complex scientific and engineering problems. Participants will examine emerging trends in AI for science, high-performance computing for machine learning, and real-world applications that demonstrate how advanced computational techniques are accelerating discovery across diverse research domains.
Paulus Shituna
Paulus is a Ph.D. student in Computer Science at the University of Namibia. His research designs AI-based Natural Language Processing (NLP) frameworks on distributed HPC infrastructure. He holds both a BSc in Computer Science and an MSc in Information Technology from the University of Namibia. Paulus serves as the Student HQ & Operations LSV for the Students@SC program. Outside of academic pursuits, Paulus enjoys coding and playing chess.
Harshita Sahni
Harshita is a final-year Ph.D. student in Computer Science at the University of New Mexico. Her research develops machine learning and high-performance computing (HPC) techniques for molecular dynamics simulations, with a focus on protein-protein interactions and real-time analysis of large-scale scientific data. She serves as the Communications LSV for the Students@SC program. Beyond her research, Harshita is an active volunteer and organizer within the high-performance computing community, having served in leadership roles at different conferences and organizations such as Women in Computing. In her free time, she enjoys badminton and spending time with family.
9 am–12:30 pm, W176a
Workshop: Workshop on High Performance Fabrics for AI and HPC
9 am–12:30 pm, W175a
Workshop: Sovereign AI Supercomputing Cloud Workshop
Panel: AI Supercomputers – Evolution or Revolution?
Paper: ACM Gordon Bell Finalists
10:30 am–12 pm, W178ab
Paper: Explaining and Debugging GPU Performance
1:30–3 pm, W185abc
Panel: Building and Managing Exascale HPC/AI Supercomputing Infrastructure
5:15–6:45 pm, W183b
BoF: Blended Infrastructure for Advanced Computational Workflows
Paper Highlight: AI Inference Becomes an HPC Systems Problem
10:30 am–12 pm, W179ab
Paper: Resource-Aware LLM Serving Pipelines
Paper: Best Papers: Accelerator-Centric Scientific Performance
8:30–9:15 am, W375de
Invited Talk: Science Is a Distributed System: Rethinking Scientific Infrastructure for the AI Era (Deborah Bard)
8:30–10 am, W178ab
Emerging computing technologies are reshaping the future of high-performance computing. This GIG explores how quantum computing and next-generation hardware accelerators are enabling new approaches to solving complex scientific and engineering problems. Participants will learn about quantum algorithms, hybrid quantum–classical workflows, specialized accelerator architectures beyond GPUs, and their integration with modern HPC systems. Through discussions of current research, real-world applications, and emerging trends, this GIG provides an opportunity to explore the technologies that are driving the next generation of computational science and discovery.
Ria Patel
Ria is a second-year Ph.D. student in Computer Science at NC State University, where she researches the integration of quantum high-performance computing (QHPC) workflows with hardware-aware pulse-level optimization. She earned her B.S. and M.S. degrees in Computer Science from the University of Tennessee, focusing on deep learning applications in classical HPC systems. Ria serves as the Student HQ & Operations LSV with Paulus for the Students@SC program. Outside of work, Ria enjoys artsy hobbies like crochet, cross-stitching, sewing, and sketching.
Befikir T. Bogale
Befikir is a Ph.D. student at the University of Tennessee’s Global Computing Lab, specializing in performance analysis for high-performance computing applications. He earned his B.S. degree in Computer Science from the University of Tennessee, with a focus on performance analysis in HPC applications. His current research focuses on enabling deeper context into compiler optimization decisions to better inform performance tuning across diverse architectures. Befikir serves as the lead student volunteer for Tutorials. Outside of work, he enjoys reading, and, sometimes, even writing stories.
9 am–5 pm, W179a
8:30 am–5 pm, W195
Workshop: Programming Novel AI Accelerators for Scientific Computing
11:15–11:37 am, W181abc
ACM Gordon Bell Finalists Presentations: Crossing the 12,000-atom Barrier with Heterogeneous Quantum-classical Supercomputing: Quantum Chemistry of Protein-ligand Complexes
11:37 am–12 pm, W181abc
ACM Gordon Bell Finalists Presentations: Closing the FeMo-cofactor “Quantum-Advantage” Gap with Exascale Supercomputers
12:15–1:15 pm, W176abc
BoF: Beyond the GPU: The Future of AI Acceleration in the Zettascale Era
1:30–2:15 pm, W375de
Invited Talk: Real Science on Integrated Quantum-Classical Computers (Peter Coveney, University College of London)
2:15–3 pm, W375de
Invited Talk: Quantum Gates Considered Harmful (Stefano Markidis, KTH Royal Institute of Technology)
10:30–11:15 am, W375de
Regional Tech Hub Talk: Before the Qubits Scale: What Quantum Can Learn from the AI Regulation Debate (David Awschalom, University of Chicago & Robert Karr, Barnes & Thornburg)
11:15 am–12 pm, W375de
Regional Tech Hub Talk: What Is Quantum and Why Should One Care? (Prem Kumar, Northwestern University)
12:15–1:15 pm, W194b
BoF: OpenQSE: Building an Open Quantum-HPC Software Ecosystem
BoF: Quantum Jumps: From NISQ to FTQC to Hybrid HPC
Paper: Compiling and Controlling Quantum Workflows
Paper: Quantum and Tensor Methods on Emerging Accelerators
Panel: HPC-Quantum Integration: Software, Systems, and Hybrid Workflows
12:15–1:15 pm, W181abc
BoF: Bringing Quantum Computing to the HPC Datacenter
1:30–3 pm, W184bcd
Panel: From Access to Impact: Designing HPC-Quantum-AI Workflows for Scientific Productivity
Panel: Beyond the Add-On: Absorbing Quantum Into the HPC Ecosystem
Artificial intelligence and machine learning are transforming how we tackle some of the world’s most challenging scientific and engineering problems. This GIG focuses on real-world applications of AI/ML across a wide range of domains, including healthcare, climate science, engineering, biology, materials science, and other data-intensive fields. Participants will explore how modern AI/ML techniques are being applied to accelerate discovery, improve decision-making, and solve complex problems at scale. Through discussions of cutting-edge research and practical use cases, this GIG will highlight the growing impact of AI/ML in advancing science, industry, and society.
Tamanna Saini
Tamanna is a third-year Ph.D. student in Computer Science at the University of Oregon advised by Dr. Brittany Erickson. Her research bridges Machine Learning and Computational Seismology, with particular emphasis on Physics Informed Machine Learning. Her work involves working with physics-informed neural networks (PINNs) to solve both forward and inverse problems related to the elastic wave equation. Tamanna serves as the Workshops lead student volunteer for the SC conference series. Outside of research, Tamanna enjoys playing outdoor sports, cooking, reading, listening to music and spending time with friends.
Ishrat Jahan Eliza
Ishrat is a third-year Ph.D. student in Computer Science at the Kahlert School of Computing and SCI Institute, University of Utah. Her research lies at the intersection of data visualization, high-performance computing, and large language models, with a focus on enabling intuitive exploration and communication of large-scale scientific data on commodity hardware through agent-based optimization strategies. Ishrat serves as the BoF and Panels Lead Student Volunteer for the Students@SC program. Outside of research, she enjoys hiking, dancing, and organizing cultural events.
BoF: Workflows Community: Next-Generation Workflows for HPC: AI, Agentic Systems, and Scientific Discovery
BoF: Data Readiness for AI in HPC: Building a Community Around Dimensions, Metrics, and Tools
Panel: Digital Twins of the Human Heart: From Exascale Simulation to Clinical Impact
5:15–6:45 pm, W179ab
BoF: Training Without Sharing: Federated Learning on the World’s HPC Systems for Science
3:30–5 pm, W181abc
Paper: MatterScale: Scaling Foundation Machine Learning Interatomic Potentials for Billion-Atom Molecular Dynamics on the Next-Generation Supercomputer
3:52–4:15 pm, W181abc
Paper: Star-LAFT: An Agent-Driven Adaptive Framework for Fault-Tolerant High-Throughput Materials Informatics
4:15–4:37 pm, W181abc
Paper: Trigger, Render, Reason: Multimodal LLM Agents for Science-Aware Scientific Simulation Monitoring
5:15–6:45 pm, W180
BoF: Inference Services and Agents on HPC: Scaling Scientific AI for Academic Community
Invited Talk: Bits to Bites: Securing the Future of Agricultural Production using AI (Ananth Kalyanaraman)
Invited Talk: Building Intelligent Systems for STEAM: From Physics to Arts (Sunita Chandrasekaran)
BoF: AI Assisted Engineering in HPC
12:15–1:15 pm, W185d
BoF: Trustworthy Data at Scale: HDF5 in the Age of AI-Driven Science
Panel: Orchestrating the Future: Heterogeneous Disaggregation at Scale for Agentic AI Workloads
What does performance really mean in high-performance computing? This GIG explores the principles and techniques behind developing fast, scalable, and portable applications for modern HPC systems. Participants will learn how to measure and analyze application performance using benchmarking, profiling, and performance analysis tools, while gaining insight into optimization strategies for CPUs, GPUs, and emerging architectures. The GIG will also cover performance portability, enabling applications to run efficiently across diverse hardware platforms. Through discussions of state-of-the-art research and practical case studies, students will develop a deeper understanding of how performance analysis drives scientific computing and next-generation HPC applications.
Tasmia Jannat
Tasmia is a Ph.D. student in Computer Science at Missouri University of Science and Technology, where she researches high-performance computing for spatial data processing, with a focus on processing-in-memory systems and irregular search workloads. She earned her B.Sc. and M.Sc. degrees in CSE from Rajshahi University of Engineering & Technology, Bangladesh focusing on hyperspectral image classification using deep learning. Tasmia serves as the Student Outreach & Networking LSV for the Students@SC program.
Greg Bolet
Greg is a Ph.D student in Computer Science at Virginia Tech under the tutelage of Dr. Kirk Cameron, where he researches automatic tuning and performance prediction of parallel codes. His work has explored the applications of optimization strategies for online/offline tuning of CPU and GPU codes. His current research is in the application of LLMs for Roofline performance prediction of GPU codes. He has been attending SC since 2018, and serves as one of the Wayfinding & Infrastructure Lead Volunteers in the Students@SC program. Outside of academics, Greg enjoys sewing, 3D-printing/CAD, thrifting, and hobby electronics!
Karame Mohammadiporshokooh
Karame is a Ph.D student at Louisiana State University as well as researcher with expertise in high-performance computing (HPC), Parallel and distributed systems, runtime systems, and performance optimization. Her work focuses on developing scalable runtime technologies, distributed graph processing algorithms for next-generation HPC applications, and the integration of runtime systems with compiler technologies, artificial intelligence, and computer architecture to enable next generation HPC systems. Karame has contributed to several research projects aimed at improving programmability and performance in modern computational technologies.
8:30 am–5 pm, W194a
Tutorial: Performance Tuning of HPC and ML/AI applications with the Roofline Model on GPUs, APUs, and CPUs
Workshop: ProTools: Eighth Annual Workshop on Visualization Instruments for Programming and Performance
10:30–10:52 am, W178ab
Paper: DeepSim: SOL-Based Explainable GPU Performance Projection with Multi-Task Learning
11:15–11:37 am, W178ab
Paper: LEO: Tracing GPU Stall Chains via Cross-Vendor Backward Slicing
4:15–4:37 pm, W178ab
Paper: Provisioning Networks for AI Supercomputers: A Trace-Driven Study of Performance Sensitivity at Unprecedented Scale
12:15–1:15 pm, W185abc
BoF: Navigating Complexity: Achieving Performance Portability in the Evolving Landscape of Accelerated HPC Systems
BoF: MPICH: A High Performance Open-Source MPI Implementation Systems
11:37 am–12 pm, W178ab
Paper: Characterizing the Scalability and Performance of Large-Scale AI Training Under Multi-Tenancy
1:30–3 pm, W175abc
Paper: Restructuring Data and Computation for Accelerator Performance
High-performance computing clusters, large-scale data centers, and large configurations all require networks operating on the principles of high-bandwidth and low-latency. In the former cases, fast networks permit large-scale HPC and AI applications to send data between servers as quickly as possible, AND serve clients efficiently. The latter allows for fast, reliable internet for end-users and “edge” devices (laptops, phones, IoT devices, etc.). This GIG takes a dive into the organizations and sessions at SC26 that focus on leveraging networks in HPC clusters for and large-scale deployment principles for fast and efficient communication across thousands of entities.
Hayden Estes
Hayden is a Ph.D. student in Computer Science at Virginia Tech, researching high-performance computing, with a focus on Energy Aware Efficiency Modeling and emerging architectures. They earned their B.S. in Computer Science from University of Alabama in Huntsville in 2023. Hayden serves as one of the SCinet LSV’s for the Students@SC program and has been a part of SCinet since 2025.
Benjamin Michalowicz
Benjamin is a Ph.D. student in Computer Science at The Ohio State University. His focus is on enhancing one-sided communication and related workloads with novel hardware such as NVIDIA’s BlueField Smart Network Cards. He earned his BS and MS in Computer Science from Stony Brook University in 2020 and 2021. Ben serves as one of the SCinet LSV’s for the Students@SC program and has been a part of SCinet since 2022. Outside of academia, Ben is an avid drummer and enjoys tabletop games such as Dungeons and Dragons.
8:30 am–5 pm
Tutorial: Understanding Communication Performance in Large-Scale Codes: A Practical Guide
2:15–3:15 pm, SCinet Booth, Exhibit Hall
SCinet NOC Guided Tour
3:30–5 pm, W178ab
Paper: Observing, Modeling, and Designing Communication at Scale
Papers in Conversation: Moving AI at Scale: Networks, Collectives, and Compression
5:15–6:45 pm
BoF: Ultra Ethernet: Next-Generation Networking for HPC Supercomputers and AI Factories
10:30 am–12 pm, W176abc
Paper: Mapping and Programming Emerging Spatial and Wafer-Scale Systems
If you have questions about Guided Interest Groups contact the Students@SC Committee. We’d be happy to help.
