Day 1 - July 20 (Morris Inn)

Workshops and Tutorials
8:00 AM - 9:00 AM
Registration Opens at Morris Inn
9:00 AM - 10:30 AM
PERMAVOST
Room: Carmichael
AI4SYS
Room: Hesburgh
QUASAR
Room: Joyce
10:30 AM - 11:00 AM
Coffee Break
11:00 AM - 12:30 PM
PERMAVOST
Room: Carmichael
AI4SYS
Room: Hesburgh
QUASAR
Room: Joyce
12:30 PM - 1:30 PM
(Lunch on Your Own)
1:30 PM - 3:00 PM
Tut.: Reproducible Perf Analysis
Room: Carmichael
FlexScience (+ FRAME)
Room: Hesburgh
QUASAR
Room: Joyce
3:00 PM - 3:30 PM
Coffee Break
3:30 PM - 5:00 PM
Tut.: Reproducible Perf Analysis
Room: Carmichael
FlexScience (+ FRAME)
Room: Hesburgh
QUASAR
Room: Joyce

Day 2 - July 21 (Duncan Student Center 7th Floor)

8:00 AM - 8:45 AM
Registration Opens at Duncan Student Center 7th Floor
8:45 AM - 9:00 AM
Welcome and Introductions

General Chairs: Douglas Thain, Jarek Nabrzyski
Program Chairs: Robert Wisniewski, Ivona Brandic

9:00 AM - 10:00 AM
Keynote #1
Abstract TBA

Speaker: Andrew Jones, Microsoft
Biography TBA

Session Chair: TBA

10:00 AM - 10:30 AM
Coffee Break
10:30 AM - 12:15 PM
Numerical Methods

Session Chair: TBA

Virtualization So Light, it Floats! Accelerating Floating Point Virtualization

Authors: Nicholas Wanninger , Nadharm Dhiantravan , Peter Dinda

FloatGuard: Efficient Whole-Program Detection of Floating-Point Exceptions in AMD GPUs

Authors: Dolores Miao , Ignacio Laguna , Cindy Rubio-González

LiteForm: Lightweight and Automatic Format Composition for Sparse Matrix-Matrix Multiplication on GPUs

Authors: Zhen Peng , Polykarpos Thomadakis , Jacques Pienaar , Gokcen Kestor

Optimization of GNN Training Through Half-precision

Authors: Arnab Tarafder , Yidong Gong , Pradeep Kumar

12:15 PM - 1:15 PM
Lunch - Duncan Student Center
1:15 PM - 3:00 PM
Model Training

Session Chair: TBA

SAFusion: Efficient Tensor Fusion with Sparsification Ahead for High-Performance Distributed DNN Training

Authors: Zhangqiang Ming , Yuchong Hu , Xinjue Zheng , Wenxiang Zhou , Dan Feng

ModelX: A Novel Transfer Learning Approach Across Heterogeneous Datasets

Authors: Arunavo Dey , Neil Antony , Aakash Raj Dhakal , Tapasya Patki , Aniruddha Marathe , Jae Seung Yeom , Tanzima Islam

FT2: First-Token-Inspired Online Fault Tolerance on Critical Layers for Generative Large Language Models

Authors: Yu Sun , Zhu Zhu , Cherish Mulpuru , Roberto Gioiosa , Zhao Zhang , Bo Fang , Lishan Yang

Optimizing Data Distribution and Kernel Performance for Efficient Training of Chemistry Foundation Models: A Case Study with MACE

Authors: Jesun Sahariar Firoz , Franco Pellegrini , Mario Geiger , Darren Hsu , Jenna A. Bilbrey , Han-Yi Chou , Maximilian Stadler , Markus Hoehnerbach , Tingyu Wang , Dejun Lin , Emine Kucukbenli , Henry W. Sprueill , Ilyes Batatia , Sotiris S. Xantheas , MalSoon Lee , Chris Mundy , Gabor Csanyi , Justin S. Smith , Ponnuswamy Sadayappan , Sutanay Choudhury

3:00 PM - 3:30 PM
Coffee Break
3:30 PM - 4:45 PM
Storage Systems

Session Chair: TBA

TSUE: A Two-Stage Data Update Method for an Erasure Coded Cluster File System

Authors: Zheng Wei , Jing Xing , Yida Gu , Wenjing Huang , Dong Dai , Guangming Tan , Dingwen Tao

AutoSSD: CXL-Enhanced Autonomous SSDs for Low Tail Latency

Authors: Mingyao Shen , Suyash Mahar , Heewoo Kim , Joseph Izraelevitz , Steven Swanson

DPU-KV: On the Benefits of DPU Offloading for In-Memory Key-Value Stores at the Edge

Authors: Arjun Kashyap , Yuke Li , Xiaoyi Lu

6:00 PM - 9:00 PM
Evening Posters and Reception in Duncan Student Center

The conference opening reception will be held in the Dahnke Ballroom on the 7th floor of the Duncan Student Center, overlooking the historic football stadium. (This is the same area as the conference main sessions.) A buffet dinner will be served, with meat, vegan, and gluten free options. The conference posters will be presented at this evening event, please use the opportunity to mingle and learn more.

Poster presentations will include the refereed poster submissions, posters from workshop papers, and posters from summer students at Notre Dame. All poster presenters are requested to set up their posters by 6:00PM, and then stand by their posters to present them from 6:30 to 7:30, after which you are free to mingle.

Presenters should print and bring their own posters, maximum of 48x36 inches. There is a FedEx Office location on campus where posters can be printed and picked up. The conference will provide easels, poster board, and tacks to mount posters.


Day 3 - July 22 (Duncan Student Center 7th Floor)

8:00 AM - 9:00 AM
Registration in Duncan Student Center 7th Floor
9:00 AM - 10:00 AM
Keynote : Physics-Aware, Full-Stack Software to Accelerate Practical Quantum Computing
Abstract Quantum software can be a force multiplier that can significantly shorten the timeline for utility-scale results from quantum hardware. In particular, several key research directions will help realize practical quantum advantage. Physics-aware, cross-layer optimizations will continue to yield important efficiencies to allow applications to make the most of quantum resources. Software-directed noise-aware optimization and error correction, in particular, will be key to increasing gate depths and maintaining acceptable output fidelity. Pulse-level optimizations and specialized native gates will also be key enablers. Additionally, applications will be hybrid computations involving high-performance classical resources as well as quantum hardware serving as special-purpose accelerators. Effectively partitioning computations between these classical and quantum resources will be necessary to support realistic applications. Additionally, deep compiler optimization and classical simulation of Clifford and near-Clifford circuits can also be important classical investments towards more efficient quantum computations. Finally, defining abstractions that control compiler complexity yet selectively expose key physical machine properties will also be a key area of research.

Fred Chong image
Speaker: Fred Chong, University of Chicago
Biography Fred Chong is the Seymour Goodman Professor in the Department of Computer Science at the University of Chicago and the Chief Scientist for Quantum Software at Infleqtion. Chong is a member of the National Quantum Advisory Committee (NQIAC) which provides advice to the President on the National Quantum Initiative Program. In 2020, he co-founded Super.tech, a quantum software company, which was acquired by Infleqtion (formerly ColdQuanta) in 2022. Chong received his Ph.D. from MIT in 1996 and was a faculty member and Chancellor's fellow at UC Davis from 1997-2005. He was also a Professor of Computer Science, Director of Computer Engineering, and Director of the Greenscale Center for Energy-Efficient Computing at UCSB from 2005-2015. He is a fellow of the ACM and the IEEE, a recipient of the NSF CAREER award, the Intel Outstanding Researcher Award, and 16 best paper awards. He is also a recipient of the Quantrell Award, the oldest undergraduate teaching award in the United States, as well as the University of Chicago's Graduate Teaching and Mentoring Award.

Session Chair: Devesh Tiwari

10:00 AM - 10:30 AM
Coffee Break
10:30 AM - 12:15 PM
Efficiency and Sustainability

Session Chair: TBA

CarbonEdge: Leveraging Mesoscale Spatial Carbon-Intensity Variations for Low Carbon Edge Computing

Authors: Li Wu , Walid Hanafy , Abel Souza , Khai Nguyen , Jan Harkes , David Irwin , Mahadev Satyanarayanan , Prashant Shenoy

Advancing Scientific Data Compression via Cross-Field Prediction

Authors: Youyuan Liu , Wenqi Jia , Taolue Yang , Jiang Bo , Miao Yin , Sian Jin

Parameterized Algorithms for Non-uniform All-to-all

Authors: Ke Fan , Jens Domke , Seydou Ba , Sidharth Kumar

Top-Down SBP: Turning Graph Clustering Upside Down

Authors: Frank Wanye , Vitaliy Gleyzer , Edward Kao , Wu-chun Feng

12:15 PM - 1:00 PM
Lunch - Duncan Student Center
1:00 PM - 2:00 PM
Industry Talk

Talk #1: The HPC Revolution: Accelerating the Future of Science and AI
Abstract High-Performance Computing (HPC) is not just a service we offer; it is part of Google's foundational DNA. This presentation explores the deep history of HPC within Google, from the early days of massive-scale indexing and distributed computing with technologies like MapReduce and Borg, to the sophisticated infrastructure that powers our global services today. We will trace this unique evolutionary path, demonstrating how decades of internal innovation in running planetary-scale workloads have directly informed the architecture and capabilities of Google Cloud's HPC offerings. Attendees will learn how this heritage translates into a robust and flexible cloud ecosystem designed to support the most demanding research challenges. Furthermore, we will delve into how Generative AI is revolutionizing the very methods of HPC development and management. We will discuss how services like Gemini Code Assist are accelerating the creation of complex simulation code and simplifying workflow scripting, while platforms like Google Colab provide an accessible environment for prototyping and analysis. Through real-world case studies in fields such as genomics and climate science, we will highlight how our infrastructure, now augmented by AI-powered tools, is empowering researchers to push the boundaries of discovery. Finally, we will look to the future, discussing how Google is continuing to democratize access to world-class HPC, fostering innovation, and helping the scientific community solve the grand challenges of tomorrow.
Sponsor image
Speaker: Charles Elliot, Google
Biography Charles Elliott is a Head of Industry at Google Cloud, leading initiatives that transform education through the power of technology, particularly generative AI. Building on a successful consulting career focused on Big Data, Analytics, and AI, Charles now leverages his extensive expertise to guide educational institutions and ed-tech companies in realizing the potential of personalized learning at scale. With over 14 years of experience, he specializes in bridging cutting-edge cloud solutions with the specific needs of the education sector. As a trusted advisor, he empowers organizations to enhance learning experiences, improve accessibility, and drive measurable educational outcomes. His work spans early childhood education, machine learning applications, and strategic cloud implementation, with a focus on leveraging generative AI to unlock new possibilities in personalized learning. Charles continues to contribute to Google's Customer Advisory Boards, fostering innovation across the industry.

Talk #2: TBA

2:00 PM - 3:00 PM
Panel Discussion

Chair: Peter Kogge, University of Notre Dame

3:00 PM - 3:30 PM
Coffee Break
3:30 PM - 4:50 PM
Clouds and FaaS

Session Chair: TBA

F3: An FPGA-accelerated FaaS Framework

Authors: Charalampos Mainas , Martin Lambeck , Bruno Scheufler , Laurent Bindschaedler , Atsushi Koshiba , Pramod Bhatotia

PathFence: Reducing Cross-Path Dependencies in Microservices

Authors: Xuhang Gu , Qingyang Wang

FluidFaaS: A Dynamic Pipelined Solution for Serverless Computing with Strong Isolation-based GPU Sharing

Authors: Xinning Hui , Yuanchao Xu , Xipeng Shen

6:00 PM - 9:30 PM
Dinner Reception at Studebaker National Museum

Join us for an evening dinner reception at the Studebaker National Museum in downtown South Bend. Conference attendees will be free to explore the entire museum full of classic vehicles and exhibits of South Bend history. A buffet dinner will be served.

Buses will leave the Morris Inn at 5:30pm, 5:45pm, 6:00pm, 6:15pm, 6:30pm, pickup people from the Inn at St Marys and the Hilton Garden Inn, and then arrive at the Studebaker Museum.

Appetizers are served from 6:00pm to 7:00pm. The buffet dinner is served from 7:00pm to 8:30pm, followed by dessert. Both meat, vegan, and gluten-free choices are available. We also serve an open bar with a selection of beer, wine, and soft drinks.

Buses will depart from the museum between 7:30pm and 10:00pm every 30 minutes, return to the Hilton Garden Inn, the Inn at St Marys, and finally the Morris Inn.


Day 4 - July 23 (Duncan Student Center 7th Floor)

8:00 AM - 9:00 AM
Registration in Duncan Student Center 7th Floor
9:00 AM - 10:00 AM
2025 HPDC Achievement Award Keynote : Designing for Trust, Transparency, and Efficiency in Scientific Computing
Abstract Today, scientific computing workflows are increasingly operating at scales where nondeterminism, opaque AI decisions, and rising energy demands are no longer exceptions—they have become the norm. In this talk, I will present the concrete methods we are using to address these challenges within the scientific discovery process. Specifically, I will demonstrate how graph-based analysis can reveal sources of nondeterminism in large High-Performance Computing (HPC) simulations, how fine-grained provenance frameworks can enhance transparency in AI-driven workflows, and how predictive engines can eliminate redundant computations in neural architecture search, thereby significantly reducing energy costs.
Beyond individual solutions, I will outline a broader vision for computing that integrates data, experiments, and computation into comprehensive scientific ecosystems, exemplified by the National Science Data Fabric (NSDF). The talk will connect technical advancements to the larger goal of producing scientific results that are trustworthy, explainable, and efficiently generated at scale.

Michela Taufer image
Speaker: Michela Taufer, University of Tennessee, Knoxville
Biography Dr. Michela Taufer, an American Association for the Advancement of Science Fellow and Association for Computing Machinery Distinguished Scientist, holds the Jack Dongarra Professorship in High-Performance Computing (HPC) at the University of Tennessee, Knoxville. She earned her B.S. in Computer Engineering (University of Padova, Italy) and Ph.D. in Computer Science (ETH Zurich, Switzerland). A former postdoctoral fellow at the University of California, San Diego and The Scripps Research Institute, Dr. Taufer is dedicated to multidisciplinary research, connecting computational and experimental sciences. Her work focuses on designing HPC, cloud, and volunteer computing solutions, applying artificial intelligence/machine learning to scientific applications, and advancing algorithms and workflows with a solid commitment to reproducibility and transparency in research.

Session Chair: Manish Parashar

10:00 AM - 10:30 AM
Coffee Break
10:30 AM - 12:15 PM
Tuning and Performance

Session Chair: TBA

Grudon: A System for Deploying Graph Workloads on Disaggregated Architectures with Near-Data Processing

Authors: Vishal Rao , Nikhil Ram Shashidhar , Ada Gavrilovska

HYPERF: End-to-End Autotuning Framework for High-Performance Computing

Authors: Juseong Park , Yongwon Shin , Junghyun Lee , Junseo Lee , Juyeon Kim , Oh-Kyoung Kwon , Hyojin Sung

Privacy-preserving of HPC Traces for Data Sharing and Analysis

Authors: Ana Luisa Veroneze Solórzano , Rohan Basu Roy , Devesh Tiwari , Benjamin Schwaller , Sara Petra Walton , Jim M. Brandt

Weight-Sharing NAS with Architecture-Agnostic Intermediate Representation

Authors: Sixing Yu , Arya Mazaheri , Ali Jannesari

12:15 PM - 1:00 PM
Lunch
1:00 PM - 2:30 PM
Best Paper and Best Student Paper Nominees

Session Chair: TBA

Out-of-Core Parallel Spatial Join Outperforming In-Memory Systems: A BFS-DFS Hybrid Approach

Authors: Lyuheng Yuan , Da Yan , Akhlaque Ahmad , Jiao Han , Saugat Adhikari , Yang Zhou

IPComp: Interpolation Based Progressive Lossy Compression for Scientific Applications

Authors: Zhuoxun Yang , Sheng Di , Longtao Zhang , Ruoyu Li , Ximiao Li , Jiajun Huang , Jinyang Liu , Franck Cappello , Kai Zhao

LegoIndex: A Scalable and Modular Indexing Framework for Efficient Analysis of Extreme-Scale Particle Data

Authors: Chang Guo , Ning Yan , Lipeng Wan , Zhichao Cao

2:30 PM - 3:00 PM
Awards and Closing Remarks

HPDC 2026 Announcement

Best Poster Award

Best Student Paper Award

Best Paper Award