SC26 Proceedings

SC Technical Program Archives

Workshops Archive

EduHPC-26: Workshop on Education for High Performance Computing


  1. EduHPC-26: Workshop on Education for High Performance Computing

  2. Featured Talk: BURGS: Breaking the Perception Barrier in Undergraduate HPC Systems Research

  3. Morning Break

  4. Validation of a Parallel and Distributed Computing Instrument for Early Computing Research

  5. A Portuguese-Language Ecosystem for HPC Education: Design, Formative Development, and Evidence of Adoption

  6. A Free Online Textbook and Interactive Exercises for Introducing Parallel Computing

  7. An AI-Anchored Pathway into HPC Practice: Design and Initial Evaluation of a Three-Day Summer School in Vietnam

  8. From a Last-Week Add-On to First-Day Practice: Three Years of Integrating MPI Performance Analysis into HPC Education with EduMPI Suite

  9. Peachy Parallel Assignments (EduHPC 2026)

  10. Mark Your Calendars: CDER Community Announcements


Back to Workshop Archive Listing


XLOOP 2026: The 8th Annual Workshop on Extreme-Scale Experiment-in-the-Loop Computing


  1. XLOOP 2026: The 8th Annual Workshop on Extreme-Scale Experiment-in-the-Loop Computing

  2. Real-time Optimization of Simulation and Data Processing Pipelines for Experiments on Exascale Computing Platforms

  3. DART: ML-Accelerated Surrogate for Real-Time CFD Digital Twins

  4. Fine-Tuning Foundation Models for Micro-CT Image Segmentation Using HPC Platforms

  5. Short Talk: When Should Quantum and HPC Systems Be Co-Located? Lessons from Real-World Workflows

  6. Morning Break

  7. Drava: An Event-Driven Runtime for Scientific Pipelines with Agentic Configuration Optimization

  8. Building Resilient Self-Driving Laboratories with the INTERSECT Federated Ecosystem

  9. Navigating the Spectrum of Science Workloads with ESnet JLab FPGA Accelerated Transport (EJFAT)

  10. Short Talk: Extending Advanced Photon Source Data Management System Workflows with Globus Streaming

  11. Every State, Every Loop, All at Once: Reaching the Outer Loop of an Autonomous Laboratory

  12. Emblase: Using Tiled as an AI-Ready Data Access Service for Live Scientific Workflows

  13. Exploring the Genesis Platform Capabilities to Accelerate Scientific Discovery in OPAL

  14. Short Talk: Portable AI Workflows and Federated Agents for Experiment-in-the-Loop Synchrotron Science

  15. Awards Ceremony and Conclusion


Back to Workshop Archive Listing


15th International Workshop on Runtime and Operating Systems for Supercomputers (ROSS 2026)


  1. 15th International Workshop on Runtime and Operating Systems for Supercomputers (ROSS 2026)

  2. ROSS'26 Invited Opening Talk: Challenges in Integrating Quantum and HPC

  3. CAPIO: Safe Kernel-Bypass of Commodity Devices using Capabilities

  4. Morning Break

  5. Mosaic: Ephemeral, Capability-Aware Scheduling Across Heterogeneous Rack-Scale Systems

  6. Resolving Placement–Residency Conflicts in Multi-GPU Task-Graph Runtimes

  7. DECARD: A Runtime for Distributed and Heterogeneous Architectures Based on Dataflow

  8. Cross-Stack Resilience for Extreme Scale AI: Coordinated Recovery for Training and Inference

  9. ROSS'26: Wrap-up discussion


Back to Workshop Archive Listing


AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC


  1. AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC

  2. Invited Talk: From Code Generation to Performance Reasoning: Agentic AI for the Autonomous HPC Stack

  3. Fabrica: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems

  4. Agentic MLIR-to-QIR Translation with Dual-Backend Testing: A Hybrid Deterministic and LLM Approach

  5. Descriptive Execution of HPC Applications and Workflows

  6. Morning Break

  7. Bridging Reasoning and Verification: A Generative AI Approach to Chemistry

  8. Towards Efficient HPC Systems for Agents: Challenges and Opportunities

  9. Diamond Agent: Agentic Control of Federated HPC Resources as a Service

  10. The Agentic Memory Hierarchy: Cross-State I/O Characterization for a Unified Substrate

  11. Building a Trusted Agentic AI system for HPC Systems Management

  12. LLMs as Packagers of HPC Software

  13. PILOT: Parallel Implementation via LLM-Oriented Translation

  14. More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow

  15. An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS

  16. ParslBox: Computational Materials Workflow Executor for AI-Agents on High-Performance Computing Systems

  17. Security Mediation and Adversarial Evaluation for Agentic AI at HPC Facilities

  18. The LLM Writes Only the Algorithm: Bit-Identical Fortran-to-C++ Substitution, and What It Certifies

  19. ScaleTether: Graph Rewriting and Selective Timing Prediction for Megatron Parallelism

  20. PROV-AGENT-LOOP: Provenance Data Management for Agentic Loop Engineering

  21. Recall Is Not Honesty: Benchmarking Multi-Agent Architectures for Trustworthy HPC Operational Analytics

  22. Distinguished Paper Recognition and Closing


Back to Workshop Archive Listing


RISE 2026: 1st International Workshop on Rising Innovators in Sustainable Exacomputing


  1. RISE Welcome Remarks

  2. Featured Speech: From Vision to Impact: Lessons in National-Scale Collaboration and Research Impact from the Exascale Era

  3. RISE Research Expertise MAP & EXHIBIT

  4. Morning Break

  5. Panel: Career Pathways Across Academia, Labs, & Industry: A Global View

  6. "Meet Your Mentor / Senior Peer" Speed Networking

  7. Women-Led Technical Project Spotlights

  8. Icebreaker and networking

  9. Rising Innovators Research Showcases

  10. RISE Closing Remarks


Back to Workshop Archive Listing


HUST-26: 13th International Workshop on HPC User Support Tools


  1. HUST Welcome

  2. Supporting a Fast-Paced National AI Resource: Portal, Identity, and Federated Access at Scale

  3. Skip the SuperPOD - The User-Driven Case for Throughput-Optimized GPU Clusters

  4. AskALCF: A Self-Improving Agentic System for Intelligent HPC User Support

  5. HUST Survey

  6. HUST Morning Break

  7. hpcGPT: A Flexible Framework for Agentic User Support in HPC

  8. From Answering to Acting: An AI Agent for Research Computing User Support

  9. HPCMosaic: Adaptive Dashboard for an Evolving HPC User Base

  10. Pelicanvil: A Web Platform for Discovering, Browsing, and Accessing Federated Datasets on HPC

  11. Compliance, ColdFront, and Chaos: Tooling to Align HPCC User Life Cycles and Research Impacts with Changing Regulatory Landscapes

  12. What Your Job Queue Isn’t Telling You: Workflow Monitoring with Drona

  13. Analyzing User Logs as a First Diagnostic Step in Open OnDemand

  14. uv-manager: A Transparent Wrapper for Safe, Architecture-Aware Python Environments on Heterogeneous HPC Clusters


Back to Workshop Archive Listing


13th Annual International Workshop on Innovating the Network for Data Intensive Science — INDIS


  1. 13th Annual International Workshop on Innovating the Network for Data Intensive Science — INDIS

  2. Featured Speaker

  3. Morning Break

  4. Security Panel

  5. National Data Platform, National Research Platform and Open Science Data Federation: How they collectively enable data-intensive science

  6. SciNet: Science-Aware Network Operations for Research Networks

  7. Measured WAN Traffic Reduction from Federated Edge AI in a Distributed Cosmic-Ray Sensor Network

  8. Network-Aware Caching in Distributed CMS XRootD Systems via Data-Driven Forecasting

  9. Characterizing Network Behavior of Distributed LLM Inference on a Four Node Edge Cluster

  10. Cross-Fabric Policy Reasoning for Hybrid InfiniBand/Ethernet HPC Systems

  11. Fine-Grained Application-Aware Congestion Mitigation with Telemetry-Tuned Weighted SRv6 Policies

  12. LLM–Driven Root Cause Analysis of BGP and BFD Flap Events

  13. Lunch Break Lunch Break

  14. Towards Efficient Vertical Federated Learning on Distributed Scientific Infrastructure

  15. FAB-Cache: A Programmable Multi-Site Caching Service for Remote Dataset Retrieval Using FABRIC

  16. ORBIT: An AI-Powered Assistant for NOC Operations in a Data-Intensive Science Network

  17. A Next Generation Multi-Terabit/sec Campus and Global Network System for Data Intensive Sciences: The Global Network Advancement Group Data Intensive Science and AutoGOLE/SENSE Working Groups

  18. Afternoon Break

  19. Quantum Computing: State of the Industry and Illinois’ Ecosystem

  20. A Multi-Task Benchmark for Time Series Foundation Models on R&E Backbone Telemetry

  21. Who Benefits from Federation? Heterogeneous Gains in Cross-Operator Network Traffic Representation Learning

  22. Research Infrastructure as enabler of New Scientific Research


Back to Workshop Archive Listing


2026 International Workshop on Performance, Portability, and Productivity in HPC


  1. 2026 International Workshop on Performance, Portability, and Productivity in HPC (P3HPC)

  2. A Study In High Performance Portability Through Layered Abstractions

  3. 14 GPU Programming Paradigms Put to the Test: Performance Portability and Halstead Difficulty in Scientific Computing

  4. Morning Break

  5. Achieving Performance Portability for Semi-Lagrangian Simulations via Automated Layout and Loop Tuning

  6. Performance Portability of Multi-GPU Hydrodynamics: SCALSALE with MPI+OpenMP Target Offload

  7. Meganeura: Vulkan and Metal as a Performance-Portability Layer for GPU Training and Inference

  8. A Performance-Portable GPU-Accelerated Solution for Particle-Particle Particle-Mesh Method using Cabana and FFTX

  9. A Multi-Layer Workflow for Diagnosing Performance Portability in RAJA Applications

  10. Lunch Break Lunch Break

  11. The Future of P3HPC in the age of Agentic Development

  12. Afternoon Break

  13. Extending the Performance Portability of Julia to Long-Vector Architectures

  14. The Price of a Single Source: Performance Portability of Chapel and Julia across CPUs and GPUs

  15. Performance Improvement of Multi-Dimensional Parallel Loops in Kokkos

  16. Mojo-Driven Performance Portability for LBM

  17. Triton Attention Backend: Portable High-Performance Paged Attention for Production-Grade LLM Inference


Back to Workshop Archive Listing


The 2nd International Workshop for Software Frameworks and Workload Management on Quantum-HPC Ecosystems


  1. The 2nd International Workshop for Software Frameworks and Workload Management on Quantum-HPC Ecosystems

  2. Welcome & Opening Remarks

  3. Invited Talk #1 - The Future of Q-HPC Software Tools and Frameworks

  4. Quantum-HPC Workflows Across Multiple Quantum Computing Platforms: Two Case Studies

  5. Morning Break

  6. Examining QRMI as a Unified Interface for Quantum-HPC Integration

  7. PauLIB: HPC Strategies for Pauli-Arithmetic-Based Quantum Computing Workloads and Simulations

  8. Rethinking QDMI: Expanding the Quantum Device Abstraction to the Software Stack

  9. System Level Energy and Cost Characterization of Hybrid Quantum–Classical Cloud Workloads

  10. Special Session - The open Quantum-HPC Software Ecosystem (openQSE)

  11. Lunch Break Lunch Break

  12. Invited Talk #2 - Hybrid Q-HPC Workflow/Workload in Scientific Computing

  13. Fidelity-Aware Scheduling of Quantum Circuits on Multi-QPU Systems

  14. The MQSS Benchmarking Framework: Extensible Orchestration Layer for Quantum Benchmarking in HPC-Integrated Ecosystems

  15. Afternoon Break

  16. QSPredictor: Runtime Prediction for Tensor-Network based Quantum Circuit Simulation on GPUs

  17. Deciding whether a generative quantum eigensolver can work before running it

  18. Dispatch Granularity in Quantum-HPC ADMM Optimization: Implications for Near-Real-Time Computing

  19. Hardware-Aware Compilation of LLM-Generated, QEC-Encoded Quantum Circuits via Constraint-Aware Graph Retrieval

  20. SemQBench: Benchmarking Decomposition-Aware Runtime Policies for Quantum-HPC Search

  21. Special Session - Research priorities and opportunities on integration of Q-HPC

  22. Panel Discussion and Q&A: Challenges in AI-enabled Q-HPC Integration

  23. Closing Remarks


Back to Workshop Archive Listing


The 9th Annual Parallel Applications Workshop, Alternatives to MPI+X (PAW-ATM)


  1. The 9th Annual Parallel Applications Workshop, Alternatives to MPI+X (PAW-ATM)

  2. PAW-ATM Intro

  3. Distinguished Speaker Talk: "Developing a task-based compressible Navier-Stokes solver - lessons learned and future developments"

  4. Morning Break

  5. Invited talk: "Distributed HPC in Julia without MPI"

  6. Invited talk: "From MPI+X to Domain-Specific Abstractions: Building Sustainable Weather and Climate Software"

  7. Reconverse: A new scheduling library for multithreaded task-based runtime systems

  8. Efficient and Portable Support for Overdecomposition on Distributed GPU Platforms

  9. End-to-end GPU-native communication in GROMACS simulations with PME task specialization

  10. CUDA-Enabled Actors: Rekindling GPU Execution in the C++ Actor Framework

  11. Lunch Break Lunch Break

  12. Parallel and Accelerated Dependent Partitioning

  13. Resource Contention in Point-to-Point Overlapping GPU Communication with NVSHMEM

  14. Distributed SpMV with HClib-Actor: A Case Study in Alternatives to MPI-Based PETSc

  15. Afternoon Break

  16. Distributed Shared Timestamped Memory

  17. A Locality-Aware Execution Model for Distributed Graph Algorithms using NWGraph and HPX

  18. Toward OpenSHMEM 2.0: Separating Memory from Execution in PGAS

  19. Panel: "Is Explicit Communication Obsolete? Compilers, Runtimes and On What Matters Next"


Back to Workshop Archive Listing


IA^3 2026 — 16th Workshop on Irregular Applications: Architectures and Algorithms


  1. IA^3 2026 — 16th Workshop on Irregular Applications: Architectures and Algorithms

  2. Invited Talk: How to Beat CPU/GPUs on both Performance and Programmability: The UpDown Graph Supercomputer

  3. Morning Break

  4. GPU-Accelerated de Bruijn Graph Traversal for Genome and Metagenome Assembly

  5. Accelerating Graph Neural Networks with Decoupled Access-Execute Architectures

  6. Parallel Shortest Hyperpath Update in Large Dynamic Hypergraphs

  7. Triple Overlap in Pipelined Krylov Methods on Multi-GPU Systems

  8. Topology-Aware Sparse Factorization for Multi-Socket NUMA Architectures

  9. Exploring Sparse Matrix Multiplication Operations on Cerebras CS-3 Platforms

  10. Accelerating GPU Datalog with Kernel Fusion

  11. Time For Questions

  12. Lunch Break Lunch Break

  13. SpSYRK: Half the Work in Distributed Sparse Matrix Multiplication

  14. Optimizing Bloom Filters on Modern GPUs

  15. Cheaper by the Batch: Shared Traversal for Genotype Graph Editing

  16. Squid: Distributed-Memory k-mer Counting for Rack-Scale GPU Clusters

  17. Time For Questions

  18. Afternoon Break

  19. MailRail: Mitigating Incast Congestion with User-space, Node-based Flow Control

  20. Efficient cosmological friends-of-friends computation with fine-grained optimizations

  21. BFS-FAR: Fragment-Local Asynchronous Relaxation with Host Reconciliation for Breadth-First Search on UPMEM

  22. Distributed Sparse P-bit Ising Machines for CPU Clusters

  23. IA^3 Debate

  24. Time For Questions


Back to Workshop Archive Listing


PMBS26: The 17th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computer Systems


  1. PMBS26: The 17th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computer Systems

  2. PMBS Welcome

  3. NVIDIA Vera: A Microarchitecture-Level Comparison with Grace, Turin, and Granite Rapids

  4. Automated Design Space Exploration of ARM CMN-Based HPC Architectures: A Case Study for the European Rhea Family Processors

  5. PMBS Discussion

  6. Morning Break

  7. Repository-Scale Performance Characterization of the IO500 Benchmark

  8. Orrery: Modeling and Simulation of GPU-direct MPI Communication with SimGrid

  9. CXDVirt: Low Latency Kernel Module Based CXL-SSD Emulation

  10. Matching Workloads to Blackwell: Power-Resolved Benchmarking of NVIDIA B200 and B300 across HPC and AI Workloads

  11. HPL and HPL-MxP at Exascale on Aurora: Performance Engineering and Characterization

  12. Performance comparison and analysis of macroscopic cross section lookup kernel on Cerebras CS-3 and NVIDIA GPUs

  13. FP64 Performance and the Limits of Ozaki Emulation on HPC Systems

  14. Lunch Break Lunch Break

  15. Benchmarking Physical GCD Placement Effects on Performance, Energy, and Co-Execution

  16. Enhancing Data Center Efficiency and Throughput by Co-Scheduling

  17. Custodian: Enabling Automatic Performance Engineering Agents on the NERSC HPC System

  18. Afternoon Break

  19. PortWarp: A Cycle-Accurate GPU-Accelerated HPC Network Simulator Using Port-per-Thread Model

  20. DMSim: Configurable Data Management Simulation Framework for Scientific Computing Grid

  21. AMAI: Algebraic Modelling of Distributed AI Computations for Symbolic Performance Analysis

  22. Scalable AMG Preconditioning for DG Neutron Diffusion Solvers on Manycore CPUs

  23. Exploiting the Interplay of Compute- and Memory-Bound kernels in MPI Applications

  24. FHE-STREAM: Characterizing Memory Access Behavior in Fully Homomorphic Encryption Workloads


Back to Workshop Archive Listing


21st Workshop on Workflows in Support of Large-Scale Science (WORKS26)


  1. 21st Workshop on Workflows in Support of Large-Scale Science (WORKS26)

  2. Welcome and Introduction

  3. Distinguished Talk: Scaling Autonomy: Federated Agentic Middleware and Serverless Systems for Scientific Computing

  4. CURATE: Leveraging LLM Agents to Compose, Catalog, and Deploy Reproducible Workflows

  5. Morning Break

  6. nFlows: Enabling Efficient Data Movement in Data-Intensive Scientific Workflows on Non-Uniform Memory Access Architectures

  7. Consumption-Aware Memory Prediction for Scientific Workflows

  8. Interoperable Performance Prediction through Standardized Metadata Capture and Analysis

  9. Offset-Aware Coalescing for Fine-Grained Scattered Reads in HPC Reproducibility Analytics

  10. Decentralized Scheduling of Scientific Workflows

  11. How far can network congestion awareness improve scientific workflow scheduling?

  12. Dynamic and Static Workflow Orchestration for Large-Scale Uncertainty Quantification Campaigns

  13. Adapting Classic List-Scheduling Heuristics for Conditional Task Graphs

  14. Lunch Break Lunch Break

  15. RLSA: Adaptive LLM Gating for Multi-Agent HPC Scheduling Agents

  16. Guarded, State-Aware Orchestration for Schema-Constrained Scientific Model Execution

  17. Agents at Your Service: Reuse-First Workflow Composition with Laminar 3.0

  18. Complexity and Scale in AI-Assisted Workflow Management: A Federated Learning Case Study

  19. Afternoon Break

  20. The Other Half of Workflow Portability: Evidence-Backed HPC Site Profiles with Agentic Discovery

  21. Enabling Radio Astronomy to Use French Supercomputers

  22. Risk-Oriented Contracts for Non-Functional Requirements in Computing-Continuum Workflows

  23. HPC-CARLA: Closed-Loop Evaluation of Autonomous Driving Agents as a Resilient, Schedulable HPC Workload

  24. Panel Discussion: Navigating the Future of Scientific Workflows

  25. Conclusion


Back to Workshop Archive Listing


AI4S: 8th Workshop on Artificial Intelligence and Machine Learning for Scientific Applications


  1. Invited Talk 1

  2. Morning Break

  3. EnvAgent: Multi-Agent Approach to Building Science Environments in the Clouds

  4. Limitations of Generative Inverse Design for Scientific Simulations

  5. Coconut: An HPC-Native Inference Framework for Neural Surrogates in MPI Simulations

  6. LightshowAI-Agent: An MCP-Based Agentic Framework for Real-Time and Reproducible X-Ray Absorption Spectral Analysis at Scientific User Facilities

  7. An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc

  8. When Agents Break the Memory Hierarchy: Understanding Data Stalls in Agentic HPC Workflows

  9. Lunch Break Lunch Break

  10. Invited Talk 2

  11. Afternoon Break

  12. Distributed Volumetric Generation of Neuronal Morphology at Scale

  13. Stabilizing Autoregressive PDE Foundation Model Rollouts with Event-Triggered Context Healing

  14. ShardTensor: Democratizing Domain Parallelism for Scientific Machine Learning

  15. A Distribution-Function GNN Surrogate for Lattice Boltzmann Flows: Adaptive Coarsening Is Where the Speedup Comes From

  16. On Multimodal Joint Embedding Predictive Architecture models for Tokamak Plasma Dynamics

  17. Scaling Laws for Physics-Aware ACOPF Surrogate Learning


Back to Workshop Archive Listing


EESP 2026: 3rd International Workshop on Energy Efficiency with Sustainable Performance: Techniques, Tools, and Best Practices


  1. EESP Welcome Remarks

  2. Featured Speech: Holistic Power Efficiency: Squeezing Computing out of Every Watt

  3. Sub-Cycle Power Measurement of AI Workloads on Production GPU Racks

  4. Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling

  5. Heterogeneous Energy Characterization of GPU-Powered Datalog Engines

  6. LASSI-EE: LLM-based Automated Refactoring of Parallel Scientific Codes for Energy Efficiency

  7. Afternoon Break

  8. A Deployment-Aware Multi-Objective Hyper-Parameter Optimization Framework for Machine Learning

  9. Adaptive Control with Offline Reinforcement Learning for HPC Power Management

  10. Energy and Cost-Aware Control at Scale: Multi-Dimensional Frequency Steering on AMD MI300A

  11. Variation-Aware Non-Uniform Node Power Capping for Exascale HPC Systems

  12. Decay-Driven Multi-Objective Reinforcement Learning for Preference-Aware Power Control in HPC

  13. Domain-Aware Power Rebalancing under Node-Level Power Caps on Aurora

  14. Saving Energy Costs and Time on Supercomputers: Scheduler-Integrated Recurring Node Shutdown Exploiting Malleable Jobs

  15. Collecting Infrastructure-Level Measures for Energy Analysis in Modern Computing Infrastructures

  16. Energy-Aware Performance Characterization of Kokkos Kernels Across Precision Levels

  17. Towards Direct-to-Chip Liquid-Cooled Megawatt Racks: Characterization of a Multi-Kilowatt Chip-Scale Cooler & The Implications on Facility Energy Use

  18. OBSERVE: An Observable, Sustainable, and Fault-Tolerant Runtime for Hyperparameter Optimization on Production HPC Systems

  19. EESP Closing Remarks


Back to Workshop Archive Listing


ISAV26: In Situ AI, Analysis and Visualization


  1. Opening Remarks by ISAV OC

  2. This Data Will Self-Destruct in One Microsecond: Live Data Reduction and Steering at LCLS-II

  3. Bridging In-Situ Visualization to Game Engines : From ParaView Catalyst via ANARI to Unreal Engine

  4. Afternoon Break

  5. Ensemble PBVR: Interactive In Situ Visualization of Ensemble Statistics on Rendering Particles

  6. PULSE: Parallel Uncertainty-guided Landscape Sampling Engine for In-Situ Molecular Dynamics

  7. Utilizing Deep Learning-Based Video Frame Interpolation for Scientific Visualization

  8. An In Situ Computational-learning Framework for the Simulation of the Cardiac Electrical System of a Patient-specific Human Heart

  9. Using Persistent Digital Twins as Spatial Environments for Robotics Simulation and Deployment

  10. N-VEG: 3D Gaussian Encoding for Neural Volume Compression

  11. An Integrated In-Situ Visualization Framework for Interactive Analysis and Surrogate Modeling

  12. A Distributed Particle-Based Volume Rendering Framework for Fugaku and Beyond

  13. Awards and Closing Remarks by ISAV OC


Back to Workshop Archive Listing


5th International Workshop on Cyber Security in High Performance Computing


  1. 5th International Workshop on Cyber Security in High Performance Computing

  2. Welcome to S-HPC 2026

  3. A Threat Model for Sensitive-Data Workloads on Multi-Tenant AI Supercomputers

  4. Privacy Foundations for Multi-Institutional Scientific Artificial Intelligence

  5. A First Look at Conventional Attacks on Scientific Applications

  6. Afternoon Break

  7. Distinguished Speaker

  8. TMD - A Label-Free, Misalignment-Robust Distance for HPC Attack Detection

  9. Quantifying Workload Exposure in HPC Power Telemetry at Operational Sampling Rates

  10. Towards Distributed-Memory All-Pairs Reachability over Homomorphically Encrypted Graphs

  11. HPC Security in the AI Era: Standards, Compliance, and Governance Panelists


Back to Workshop Archive Listing


17th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems (ScalAH'26)


  1. 17th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems (ScalAH'26)

  2. AI for Science: Building the future engines of scientific discovery

  3. Workflow-Level Scheduling of Hybrid Quantum-Classical Applications on Heterogeneous Resources

  4. Afternoon Break

  5. Scalable and Multi-NIC Parallel Trees Collective Algorithms for MPI Scatter, Gather, and Broadcast

  6. BlueField Assisted Resiliency Framework

  7. A GPU-Accelerated Blocked Adaptive Randomized Range Finder Based on an Implicit Householder QR Decomposition

  8. Gradient-Free Optimization of Quantum Circuits Parameters for Hybrid Machine Learning

  9. Exploiting Memory Contiguity in Stencil Applications for Extreme Scalability on Heterogeneous Supercomputers

  10. IRISX: Performance Portable Scientific Computing via Code Generation and Runtime Co-Design


Back to Workshop Archive Listing


High Performance Python for Science at Scale


  1. High Performance Python for Science at Scale

  2. HPPSS Featured Speaker

  3. AI for Science with Python on AMD Supercomputers

  4. Afternoon Break

  5. sundials4py: state-of-the-art time integrators for high-performance Python

  6. Python as the Connective Tissue of the Genesis Mission: From Exascale Workflows to Federated Scientific Agents

  7. A Distributed HPC/AI Services Ecosystem for the Genesis Mission Platform

  8. Python-Based Distributed Training on AMD GPU Supercomputers: Lessons from Data, Pipeline, and Tensor Parallelism on LUMI

  9. Beyond FLOPS and Kernels: Benchmarking Agentic Science and the Future Role of Python


Back to Workshop Archive Listing


Sovereign AI Supercomputing Cloud Workshop


  1. E4S: An HPC-AI Software Ecosystem for Science

  2. Building a Kubernetes-first, sovereign HPC system: OpenCUBE

  3. Morning Break

  4. OpenCHAMI for Deployment of Inference Services

  5. Sovereignty above the scheduler: pluggable site policies and a federated view for AI/HPC with Waldur

  6. AI4S and Sovereign Supercomputing in Japan

  7. EESSI as a Vendor-Neutral, Community-Driven Stack for Heterogeneous HPC and Cloud


Back to Workshop Archive Listing


Workshop on High Performance Fabrics for AI and HPC


  1. Workshop on High Performance Fabrics for AI and HPC

  2. The NSF Leadership Computing Facility and the Rising Importance of Interconnects in the (AI+)HPC World

  3. Slingshot as a First-Class Kubernetes Resource: Bare-Metal RDMA for Multi-Tenant AI

  4. Morning Break

  5. Evaluating In-Network Collectives for AI/ML Workloads with ATLAHS

  6. LinkPass: Transparent RDMA Link Failover and Recovery for Collective Communication

  7. Enabling Topology-Awareness for Performance Improvement: A Case Study with Trinetra-A HPC Network

  8. RDMA control over lossy Ethernet: A new approach using synchronized clocks

  9. Workload-Derived Requirements for Reconfigurable AI/HPC Fabrics

  10. Predict Before Replay: Joint FEC and Flight Control for Reliable Scale-Up Links

  11. AAFLOW+: Stateful Operator Abstraction with Distributed KV Cache Orchestration for Multi-Agent Workflows

  12. Using ethtrace to debug AI networks


Back to Workshop Archive Listing


High Performance Computing for Environmental and Earth Sciences (HPC4EES)


  1. High Performance Computing for Environmental and Earth Sciences (HPC4EES)

  2. On Big Data, Big Simulations, and Big plans for AI in Climate Sciences

  3. Morning Break

  4. Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform’s Communication Bottleneck

  5. Adaptive Block Mixed-Precision Cholesky Factorization for Large-Scale Space-Time Gaussian Processes

  6. Efficient Bayesian Spatially Clustered Factor Analysis with Adaptive Parallel Gibbs Sampling

  7. Short Break

  8. Portable, High-Performance and Differentiable Ocean Simulations with Unstructured Grids in Julia

  9. Rapid Earthquake-to-Tsunami Waveform Generation via Large-Scale Multi-GPU FFT Convolution Applied to the Cascadia Subduction Zone

  10. Modernizing Hercules for GPU-Accelerated Earthquake Ground Motion Simulation on NVIDIA GPUs

  11. Closing Remarks


Back to Workshop Archive Listing


Twelfth International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC 2026)


  1. Twelfth International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC 2026)

  2. Porting Codes to the NextSilicon Maverick-2 Dataflow Architecture: Early Experience, Best Practice and Performance

  3. Wafer Scale Acceleration of Unstructured Finite Element Methods

  4. To SIMD Or Not To SIMD: Comparing RVV vs. CGRA SoCs For Non-Linear Functions In AI

  5. A Highly Optimized Double-Word Arithmetic Implementation using Versal DSPs

  6. Morning Break

  7. Energy-Efficient Streaming FPGA Accelerator for DeepSeek Sparse Attention Decode

  8. SOO, MOO, and FOO: Transformer-Layer Execution on Ryzen AI NPUs

  9. Rapid Dataflow Buffer Sizing for DNNs via Parallel RTL Control-Flow Simulation for FINN

  10. High Speed Network Processing for Scientific Computing in the Open Cloud Testbed

  11. Profiling and Optimization Opportunities for SmartNIC-Assisted MoE Inference

  12. GarageWork: A Shared Testbench Abstraction for Software Simulation and FPGA Testing

  13. BASE: A Reusable Streaming Preprocessing Accelerator for Heterogeneous FPGA Systems

  14. Machine Learning for a Gamma-Ray Telescope Using Stream-HLS

  15. Closing Remarks


Back to Workshop Archive Listing


10th International Workshop on Software Correctness for HPC Applications (Correctness '26)


  1. Welcome

  2. Invited Talk: Genesis Mission and the Next Generation of Verified Scientific Workflows

  3. A Tool Infrastructure for Runtime Correctness Checking of Device-Initiated Multi-GPU Communication

  4. Reducing Confusion and Broadcasting Understanding: An Empirical Study of the Semantics of NCCL

  5. Morning Break

  6. Tighter error bounds using structural floating-point properties and tail bounds

  7. Evaluating Function-Level Accuracy and Performance of SIMD Math Libraries with FP32 Inputs

  8. A Probability-Based Static Analysis to Lower Overhead in Floating-Point Exception Detection in NVIDIA GPUs

  9. PaFEx: Cross-platform Floating-point Exception Detection using LLVM and PAPI

  10. Parameterized Verification of Deterministic MPI Programs

  11. Verification of PETSc with CIVL using LLM-generated ACSL contracts and deterministic driver generation

  12. Developing a Numerical Algorithm with CIVL Model Checking in the Loop

  13. LASSI-Verify: Adaptive Empirical Verification of LLM-Generated Parallel Scientific Code Transformations


Back to Workshop Archive Listing


6th International Workshop on RESource DISaggregation in High Performance Computing (RESDIS)


  1. 6th International Workshop on RESource DISaggregation in High Performance Computing (RESDIS)

  2. Opening Invited Talk: Tightly Coupled and Customizable Heterogeneity

  3. Past the FLOPS Era: Memory-Bandwidth Disaggregation as a Design-Space Coordinate for LLM Accelerators

  4. Morning Break

  5. CoDISAR: A Composable Disaggregated Infrastructure for SAR Backprojection

  6. Congestion-Aware Collective Communication for Composable Disaggregated GPUs

  7. Impact of Overheads in Disaggregated Systems on Job Turnaround Times

  8. Towards Server-Grade Device Pooling over Routable PCIe with Improved and Scalable Systems Software

  9. Green Shift: Resize the GPU, Not the Process


Back to Workshop Archive Listing


Research Software Engineers in HPC (RSE-HPC-2026)


  1. Research Software Engineers in HPC (RSE-HPC-2026)

  2. RSE-HPC Invited Talk

  3. RSE-HPC Lightning Talks 1

  4. Morning Break

  5. RSE-HPC Lightning Talks 2

  6. RSE-HPC Short Break

  7. RSE-HPC Panel: Meeting RSE Challenges


Back to Workshop Archive Listing


PDSW’26: The 11th International Parallel Data Systems Workshop


  1. PDSW’26: The 11th International Parallel Data Systems Workshop

  2. The Relationship Between AI and Research Data Management

  3. Morning Break

  4. GPU-Aware h5py: A Pure-Python Extension for HDF5--GPU Data Movement

  5. GPUH5: A GPU-first I/O Library for Scientific Data

  6. Dynamic Planning for Scalable Data Movement in Accelerated Query Engines

  7. GDSight: Per-Operation Cross-Layer Attribution for GPUDirect Storage

  8. Stress-Testing Exascale Scientific Data Output - ADIOS2 Configuration Strategies for WarpX under Extreme Load Imbalance

  9. Correctness Evidence for I/O Optimizations in VPIC-Kokkos: Preliminary Results

  10. Trigger-Gated Multimodal LLM Agents for In-situ Scientific Simulation Monitoring

  11. Fair, Random IO Operations are Hard

  12. One Bus Accident Away from Death: The Fragility of HPC I/O Tools

  13. Lunch Break Lunch Break

  14. Sharing a Fabric with Collective Communication: Two Storage Penalties in DL Training

  15. Copy2: Data Sync Tool For High Performance Storages

  16. Measurement-Driven Contention-Aware, Herd-Safe Stripe Placement for Lustre

  17. Afternoon Break

  18. STARCH: RPC-Lifecycle Tracing of Margo-Based Distributed Systems for Performance Analysis

  19. PRISM: Lightweight Surrogation for Lossy Compression Quality Prediction

  20. Large Scale Sorting on UPMEM Processing-in-Memory Architectures

  21. DAOS Update: Version 2.8 and MLPerf Storage

  22. Exploring DAOS as a Burst Buffer for Nx100 Gbps Scientific Streaming

  23. Move Metadata, Not Data: A Register-in-Place Lakehouse for Large Autonomous-Driving Datasets

  24. Type-Safe, Dynamically Defined Metadata Support for Scientific Applications

  25. AI Agents for Data Infrastructure: From Telemetry to Optimization

  26. GPU-Initiated Data Movement for Accelerator-Centric HPC

  27. DPUCrumbs: Dissecting DPU Pathways

  28. Towards PIM-Aware Expert Decomposition and Mapping for MoE Inference


Back to Workshop Archive Listing


LLVM-HPC2026: The Twelfth Workshop on the LLVM Compiler Infrastructure in HPC


  1. LLVM-HPC2026: The Twelfth Workshop on the LLVM Compiler Infrastructure in HPC

  2. CUDA Tile

  3. Morning Break

  4. Zero-Overhead Polymorphism on GPGPUs with LLVM Just-in-Time Compilation

  5. Multilingual GPU Communication Libraries with LLVM Bitcode and CUDA LTOIR

  6. GPU Code Generation for OpenACC Kernels construct in a Modern MLIR-Based Compiler

  7. Bringing OpenACC to LLVM’s Offload Stack: Dialect Contracts, Lowering Boundaries, and a First-Class ACC Runtime

  8. Lunch Break Lunch Break

  9. Afternoon Session Introduction

  10. Learning When to Unroll-and-Unmerge on GPUs: Experiences with Reinforcement Learning in LLVM

  11. GPU Device Compilation in ClangIR: Lowering CUDA and HIP Kernels Through the CIR Pipeline

  12. Code Generation with MLIR for the OPS Structured-Mesh DSL

  13. Platform-Agnostic Kernel Fusion Pipeline for Linear Algebra Kernels in MLIR

  14. Who You Gonna CALL? Static Whole-Program Call Graphs for Fortran

  15. Evaluation of LLVM Flang for Production HPC Applications and Modern Fortran Features

  16. Linalg vs MDH: Why Reduction Semantics Matter

  17. An LLVM Pass for Automatic Skeletonization of MPI Applications

  18. Short Talks Wrap-up

  19. Afternoon Break

  20. A Production Compiler Implementation of Hardware Transactional Memory for OpenMP

  21. Keeping up the Pace: Growing AMD Flang's OpenMP Offloading Ecosystem

  22. Evaluating OpenMP API Version 6.1 Target Kernel Language

  23. Instrumentor: Customizable and Generic Instrumentation for LLVM


Back to Workshop Archive Listing


2nd Annual Workshop on Large-Scale Quantum-Classical Computing (LSQCC)


  1. 2nd Annual Workshop on Large-Scale Quantum-Classical Computing

  2. Plenary Talk: Jerry Chow

  3. Plenary Talk: Tanner Crowder

  4. Morning Break

  5. Algorithms & Applications

  6. QC-HPC Ecosystem

  7. Lunch Break Lunch Break

  8. Software for Large Scale Application

  9. Afternoon Break

  10. Software for Large Scale Application (2)

  11. National Lab Strategies


Back to Workshop Archive Listing


8th Workshop on Programming and Performance Visualization Tools (ProTools)


  1. 8th Workshop on Programming and Performance Visualization Tools (ProTools)

  2. HPC means Heterogeneity, Performance and Complexity

  3. Morning Break

  4. Orion: Observability framework for hybrid workflow-centric I/O monitoring in HPC systems

  5. DataCrumbs: Efficient Cross-Layer Data Capture for Explainable I/O Performance in HPC Storage Stacks

  6. Probe Less, Learn More: Characterizing and Correcting eBPF Instrumentation Overhead

  7. PInsight: Enabling In-Situ Performance Analysis for Parallel Applications

  8. A Heuristic Based Cache Miss Classifier

  9. Lunch Break Lunch Break

  10. Accelerating HPC Performance Analysis with AI Agents

  11. Afternoon Break

  12. Deriving Vendor-Agnostic GPU Metrics from AMD MI300A and NVIDIA H100 Hardware Counters

  13. Fantastic Hardware Counters and How to Use Them for Noise-Resilient Performance Modeling

  14. An Omnistat-Guided Workflow for Energy-Efficiency Analysis

  15. A Unified Semantic Interface Specification for Parallel Programming Tools

  16. Novel Profiling Pipeline for Replay-Based Performance Analysis


Back to Workshop Archive Listing


WHPC: Building Community, Building Careers


  1. WHPC: Building Community, Building Careers

  2. Super(comptuing) Heroes

  3. Morning Break

  4. Welcome Remarks

  5. WHPC Distinguished Speaker: From Silent 700s to El Capitan: Mentors and Community Made All the Difference

  6. Building a Local Chapter as Civic Infrastructure: Chicago Women in HPC and the Quantum × HPC Pathways Initiative

  7. WHPC Global Activities and Efforts

  8. ACM SIGHPC Fellows Lightning Talks

  9. Lunch Break Lunch Break

  10. WHPC Rising Starts Lightning Talks

  11. Building Research Computing Capacity Through Collaborative Visualization

  12. Evolution in Scientific Deep Learning: A Data-centric Study

  13. Connecting Skills, Training and Community: Lessons from Building the HPC Workforce

  14. Anchor: Delivering Consistent Performance on Noisy Cloud-Based Quantum Computers

  15. Hardware Aware Evaluation for Statistical Estimators: A Selection Rule and Reproducible Benchmark

  16. Predicting and Explaining Alzheimer Disease Using UK Biobank: An Auditable, Cost-Sensitive HPC Pipeline for Feature Discovery

  17. Wafer-Scale Unstructured Scientific Computing

  18. Toward Software-Defined Performance Optimization for Emerging Quantum Systems

  19. Extending the Life of HPC Systems in Resource-Constrained Environments: A Path from a Student Cluster Competition to Sustainable Computing in Africa

  20. Leveraging high performance computing for simulation of snowpack liquid water content using SnowModel

  21. Prefetching in Disaggregated Memory Systems

  22. Accurate and Scalable Graph AI for Early and Explainable Health Risk Assessment

  23. WHPC Networking Breakout

  24. Afternoon Break

  25. WHPC Career Pathways

  26. WHPC Closing Remarks

  27. WHPC Newcomers Session


Back to Workshop Archive Listing


HPC Systems Professionals Workshop (HPCSYSPROS26)


  1. HPC Systems Professionals Workshop (HPCSYSPROS26)

  2. Enabling Performance Isolation for Co-scheduled Workflows

  3. Operationalizing Workflow Support on Slurm: A Site Toolkit for Choosing Nextflow Deployment Strategie

  4. Morning Break

  5. Obleth: Fair Multi-Tenant LLM Serving for Self-Hosted Campus Infrastructure

  6. HPC Infrastructure Management at Scale

  7. Ops Knowledge That Stops Evaporating: Building an Evergreen Documentation, Search, and Monitoring System on an Agent CLI

  8. Architecting Multi-Petabyte Data Migration in a Live HPC Environment: From Strategy to Execution

  9. Lunch Break Lunch Break

  10. Subsurface to Stellar: HPC Enablement with Open OnDemand and ColdFront at bp and NASA

  11. Experiences with and Best Practices around Cooling Distribution Units (CDUs)

  12. Afternoon Break

  13. The Evolution of the Coaraci HPC Infrastructure: Operational Lessons from a Brazilian Research Computing Center

  14. Faster Post-Outage Testing at Full Machine Scale

  15. Security and Day-2 Resilience as First Class Control Plane Primitives for Heterogeneous Supercomputers

  16. Death by a Thousand Spreadsheets: Consolidating Infrastructure Data with NetBox

  17. Teaching HPC to Advanced High School Students at a Summer Program


Back to Workshop Archive Listing


8th International Workshop on Containers and New Orchestration Paradigms for Isolated Environments in HPC (CANOPIE-HPC)


  1. 8th International Workshop on Containers and New Orchestration Paradigms for Isolated Environments in HPC (CANOPIE-HPC)

  2. Simplifying Compute Access for RL Use Cases at Scale

  3. Benchmarking Agentic AI Workflows with Charliecloud

  4. Morning Break

  5. Agentic Orchestration of HPC Applications in Cloud

  6. No-Restart Elasticity in an Adaptive Runtime System for Cloud-Native HPC

  7. Characterizing LLM Inference Performance on a WebAssembly Runtime

  8. Parallel Restore-Optimized Snapshot Compression for Cost-Efficient Inference Serving

  9. Lunch Break Lunch Break

  10. The American Science Cloud and the Genesis Mission

  11. Charliecloud: Image Build Optimization for AI Workloads

  12. Secure integration and scaling for thousands of Jupyter sessions across hybrid cloud and HPC resources on Anvil

  13. Afternoon Break

  14. CI for E4S: Build and Test Automation for a Containerized HPC-AI Software Stack

  15. Expanded Slurm container runtime support

  16. The Bipartible Architecture Pattern: Transparently Directing HTTP Requests over InfiniBand

  17. Optimizing Podman Storage Performance on Shared Filesystems

  18. Overlay Containers in Apptainer

  19. The case for unprivileged containerization in HPC, or: Does software simplicity still matter in 2026?

  20. Community Discussion and Q&A


Back to Workshop Archive Listing


Sixth International Symposium on Quantitative Co-Design of Supercomputers


  1. Sixth International Symposium on Quantitative Co-Design of Supercomputers (SQCS)

  2. Opening Remarks from Workshop Chair

  3. Lead Invited Talk (Satoshi Matsuoka, Director of Riken Center for Computational Science)

  4. Afternoon Break

  5. Deep codesign of advanced technology systems

  6. Co-Designing the NIC and Transport: Simpler Hardware, Scalable Communication

  7. Co-Design for new processor and system architectures at JSC

  8. Moderated Panel Discussion

  9. Closing Remarks


Back to Workshop Archive Listing


The 12th Computational Approaches for Cancer Workshop (CAFCW26)


  1. The 12th Computational Approaches for Cancer Workshop (CAFCW26)

  2. Welcome and Introduction

  3. Opening Panel Discussion - Uniting Research, Clinic and Patient

  4. CAFCW26 Virtual Posters

  5. Afternoon Break

  6. Addressing Challenges in Collaborative Computational Cancer Policy Research

  7. PathLlama: Domain-Adapted Language Models for Cancer Surveillance at Scale

  8. Geometry-Routed Attention for Multi-Magnification Histopathology Fusion in Oral Squamous Cell Carcinoma

  9. Stretch Break

  10. PDO Drug Screening Studies for Evaluating and Training AI Drug Response Prediction Models

  11. Auditing drug-response transfer at scale: an HPC-parallel, IMPROVE-conformant control pipeline

  12. Wrap-up and Closing Remarks


Back to Workshop Archive Listing


FTXS: Workshop for Faults, Trustworthiness, and eXplainability for AI Systems at Scale


  1. FTXS: Workshop for Faults, Trustworthiness, and eXplainability for AI Systems at Scale

  2. (Featured Speaker) From Recovery to Explanation: Deterministic Replay as Evidence for Fault Diagnosis at Scale

  3. Afternoon Break

  4. Characterizing Failure Types Across HPC and AI Clusters

  5. Domain Bounds as a Silent-Fault Detector for AI-Ready Scientific Data

  6. Asynchrony Promotes Scalable Recovery of Iterative Linear Solvers from Silent Errors

  7. Studying Silent Data Corruption Sensitivity of Precision Reduction Techniques during Deep Neural Network Training

  8. ARC-FL: Fault-Tolerant Federated Learning via Error-bounded Lossy Compression and Unequal Error Protection

  9. FTXS 2026 : Closing remarks


Back to Workshop Archive Listing


ExaMPI26: Workshop on Extreme-Scale MPI


  1. Invited Talk: Torsten Hoefler: AI Infrastructure at Hyperscale - The Role of (Ultra) Ethernet

  2. Afternoon Break

  3. MPI-CCOB: Benchmarking MPI Overlap on CPU and GPU Systems

  4. Extending MPI One-Sided Communication with Lightweight Notification-Based Synchronization

  5. Scalable Hierarchical Multi-NIC GPU-Aware MPI Alltoall via Hamiltonian Decomposition

  6. Execution-Path- and Restriction-Aware Autotuning for MPI Collective Operations

  7. MPI Windows as an Abstraction for CUDA Interprocess Communication


Back to Workshop Archive Listing


7th Workshop on Heterogeneity and Memory Systems (HMEM)


  1. Featured Talk: Hotness tracking in CXL hardware

  2. Afternoon Break

  3. Optimizing system memory bandwidth with micron CXL memory expansion modules on intel Xeon 6 processors

  4. One API, Five Memories: Measuring Unified Memory Across NVIDIA and AMD Architectures

  5. Extending ecoHMEM to Arm: Automatic Data Placement Using Statistical Profiling Extension

  6. An ELF-Aware DMA Engine for Distributed-Memory Accelerators


Back to Workshop Archive Listing


High-Accuracy Computing on Low-Precision Hardware


  1. High-Accuracy Computing on Low-Precision Hardware

  2. Invited Talk with Eric Nielsen, Senior Research Scientist with the Computational AeroSciences Branch at NASA Langley Research Center

  3. Mixed-Precision Cholesky Factorization for Semidefinite Programming Using Ozaki Scheme II

  4. No Bits Left Behind: A Precision-Preserving On-Wafer Reduction for FP64 GEMM

  5. Afternoon Break

  6. Invited Talk with Rob Schreiber, Distinguished Engineer at Cerebras Systems

  7. Error-Explicit Low-Precision Factorizations for Iterative Refinement

  8. Optimizing Semiconductor Device Simulations through Low-Precision Arithmetic

  9. DGEMM with Ozaki Scheme I/II on FP4 Tensor Cores: A Base-13 E2M1 Limb Representation

  10. Mixed Precision at Scale: From Peak FLOPs to Trusted Science


Back to Workshop Archive Listing


AI on HPC: Performance Engineering, Challenges and Opportunities


  1. AI on HPC: Performance Engineering, Challenges and Opportunities

  2. OPSERVE: Opportunistic LLM Inference over Fragmented GPU Capacity in HPC Systems

  3. Performance Characterization of GPU Sharing Strategies for LLM Inference

  4. LLBPE: Linked-List Based GPU-Parallel BPE Tokenizer

  5. Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware

  6. MiniLlama-Infra: Micro-Architecture Ablation of LLM Inference on Commodity GPU Accelerators

  7. Afternoon Break

  8. T-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory Accelerator

  9. Analytical Resource Management for Fine-Grained MoE Computation-Communication Overlap

  10. Characterizing and Auto-Tuning 175B-Parameter LLM Training on Intel Data Center GPU Max 1550 Accelerators

  11. Co-designing MoE Architectures and System Stacks for Scalable Training on Leadership Supercomputers

  12. Adopting Emerging AI Frameworks in HPC Environments

  13. Theoretical and Empirical Analysis of Sparse Convolution

  14. A Comparative Study of Energy Scaling Behavior for AI Training: Wafer or Die Scale

  15. HOLOS: A Gradient-Descent-Based Design-Space Exploration Framework for Hierarchical AI Accelerator Systems

  16. Watts Behind the Weights: Characterizing Energy Consumption of the AI Training Lifecycle in HPC

  17. Characterizing Simulation-AI Coupled Workflows on Frontier: Benchmarks and Digital-Twin Replay


Back to Workshop Archive Listing


International Workshop on RISC-V for HPC (RISCVHPC)


  1. International Workshop on RISC-V for HPC (RISCVHPC)

  2. Invited talk: HPC from the RISC-V International perspective

  3. A JIT framework for Implicit GEMM and FlashAttention Micro-Kernels in RISC-V

  4. Investigating ET-SoC-1 Vector and Parallel Performance with sGEMM

  5. Machine Learning-Based Performance Prediction for RISC-V Vector (RVV) Processors

  6. TSVC-RVV: A Diagnostic Extension of TSVC for Evaluating RISC-V Auto-Vectorization

  7. Morning Break

  8. Porting and Benchmarking Chapel on Emerging RISC-V Hardware: An HPC Viability Study

  9. A community developed simulator for the Tenstorrent Tensix architecture

  10. Scale Up Platform Enabled by RISC – SUPER

  11. Hitting the Memory Wall: Why Cache Miss Tolerance Defines CPU Performance Now

  12. Accelerating Fast Fourier Transforms with the RISC-V Vector Extension


Back to Workshop Archive Listing


Fourth International Workshop on HPC Testing and Evaluation of Systems, Tools, and Software (HPCTESTS 2026)


  1. Fourth International Workshop on HPC Testing and Evaluation of Systems, Tools, and Software (HPCTESTS 2026)

  2. JUPITER: From Consistent Imaging to Continuous Benchmarking

  3. ClusterBench: A Framework for Cluster-Wide Continuous Benchmarking and Regression Testing

  4. Tracking HPC Software Stack Drift and Performance with Benchpark

  5. Morning Break

  6. The Shape of Speed: Impacts of Partition Geometry and Rank Density in Distributed Quantum Circuit Simulations

  7. Diagnosing and delivering repairs for Fortran GPU offload compiler defects

  8. Mechanism-Aware Analysis of Cross-Platform GPU Fault-Injection Outcomes

  9. HPCTESTS Panel 2026


Back to Workshop Archive Listing


Thirteenth SC Workshop on Best Practices for HPC Training and Education


  1. Thirteenth SC Workshop on Best Practices for HPC Training and Education

  2. HPC Education and Training: Emerging Opportunities and Challenges

  3. How the Paradigm of Scientific Computing Evolves Through the Genesis Mission

  4. HPC Education Across Institutional Boundaries: Leveraging NCShare's Statewide Cyberinfrastructure

  5. Measuring the Impact of the Better Scientific Software Fellowship Program

  6. Sustaining Early-Career Talent Through an HPC Bootcamp Pipeline

  7. Lowering the Barrier: Leveraging JupyterHub for K–12 AI and Data Science Outreach

  8. Morning Break

  9. Empowering K-12 Education through HPC-enabled AI and Computational Thinking: A Living Lab Case Study

  10. The Cornell Virtual Workshop: Looking Back, Looking Forward

  11. From dispersed training materials to a centralized learning solution: The conceptualization of the SDSC Learning Hub

  12. A Scalable and Sustainable Online Environment for HPC Education: Integrating projectEUREKA! with Local Kubernetes Infrastructure

  13. The Art of the Hack: Deconstruct--Reconstruct--Apply as a Constructionist Framework for AI-Enabled Gateway Development

  14. Beyond the helpdesk: a lightweight, reproducible model for just-in-time HPC learning and support

  15. Beyond Job Submission: Developing System Literacy through Productive Struggle

  16. Q/A and Closing Remarks


Back to Workshop Archive Listing


4th Annual Trillion Parameter Workshop: Building Open AI Infrastructure, Models, and Agentic Systems for Science


  1. 4th Annual Trillion Parameter Workshop: Building Open AI Infrastructure, Models, and Agentic Systems for Science

  2. Pre-Training AuroraGPT on Intel XPUs

  3. Can LLMs Write Task-Based Parallel Code?

  4. Proper Rewards: Post-Training Time Series Foundation Models with Scoring-Rule GRPO

  5. From Pilots to Production: Lessons in Cross-Institutional Federated Training and AI for Science

  6. ArchAgent: Agentic AI for Heterogeneous System Design Across Chip, Scale-Up, and Scale-Out Domains

  7. A Tale of Two Teams: Scientists Versus the Multi-Agent System

  8. Buffer

  9. Morning Break

  10. Governed Agents: An Evidence-Based Architecture for the Computing Continuum

  11. APEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction

  12. AI Agents for Nuclear Science: Evaluation of Vaults, Skills, and Multi-Agent Verification

  13. From Candidate to Confirmed: A Verification-First Agenda for Open Autonomous Science

  14. Invited Talk: Victor Fung (Georgia Tech & Lila Sciences)


Back to Workshop Archive Listing


Thirteenth Workshop on Accelerator Programming and Directives (WACCPD 2026)


  1. Thirteenth Workshop on Accelerator Programming and Directives (WACCPD 2026)

  2. The Amazing World of Programming for Accelerators: From GPUs to SmartNICs and QPUs (Among Many Others)

  3. Evaluating Fused Weight-Decompression General Matrix Multiplication for Quantized LLM Inference in SYCL

  4. Towards Performance-Portable GPU Acceleration of MOM6 with Standard Fortran and OpenMP

  5. Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath

  6. Morning Break

  7. Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI

  8. Annotation-Driven Migration of CUDA Programs to Tenstorrent Blackhole

  9. Dependency-Preserving GPU Work Decomposition for Earthquake Rupture Simulation Using the Fast Domain Partitioning Method

  10. JACC.Async: Performance-Portable Asynchronous Multi-GPU Programming with Just-in-Time Compilation

  11. JForce: Fortran on AI Hardware via OpenMP Offloading and XLA JIT Compilation

  12. Load-Balanced Communication Overlap for Lattice H-Matrix–Vector Multiplication on GPU Clusters


Back to Workshop Archive Listing


Sustainable Supercomputing


  1. Sustainable Supercomputing

  2. Welcome

  3. Invited Talk - Title TBD

  4. Fast and Accurate ML Surrogates from Simulation: An HPC Liquid-Cooling Models Case Study

  5. EcoShift: Performance-Aware Power Management for Power-Constrained Heterogeneous Systems

  6. Morning Break

  7. Compositional Energy Modeling of Layer-Resolved GPU Training

  8. From GPU-Accelerated Systems to Modern NVIDIA and AMD Superchips: Analyzing Energy and Power of a Heterogeneous SYCL Application

  9. Does New Hardware Improve Carbon Impact of HPC systems?

  10. Predicting the Energy-Optimal GPU Clock for Production VASP Jobs Before They Run

  11. The Economic Value of Heat Reuse


Back to Workshop Archive Listing


Workshop on Operational Data Analytics in HPC (HPC-ODA)


  1. Workshop on Operational Data Analytics in HPC (HPC-ODA)

  2. A case study on the resource utilisation and queue dynamics of an institutional HPC system

  3. On preprocessing heterogeneous HPC telemetry for use in foundation models and digital twins

  4. Perlmutter-Agent: Design and Early Deployment of a Local, Tool-Grounded LLM Assistant for HPC Incident Investigation

  5. SORT: Slurm-Orchestrated ROCm Telemetry for Facility-wide GPU Observability on HPC Systems

  6. What is Your Cluster Actually Doing? Understanding Users, Utilization, and Performance Through Extensive Slurm Job Data Analysis

  7. Morning Break

  8. Interactive Visualization of Data Center Monitoring Data on a 3D Cluster Model

  9. TULCA-Based Visual Analytics of HPC Operational Data: A Case Study of Fugaku Rack's Power Data

  10. CQTwin: A Digital-Twin Toolkit for Operational Analytics of HPC Schedulers

  11. Emerging Personas and Tools for Hybrid Quantum-HPC Systems

  12. Data-Driven Static MIG Planning for an H200 Research Cluster

  13. Towards MPI Communication Modeling From Passive Network Telemetry


Back to Workshop Archive Listing


Scale to See: Scalable AI for Scientific Imaging and Spatiotemporal Data


  1. Scale to See: Scalable AI for Scientific Imaging and Spatiotemporal Data

  2. Scale to See: From Extreme-Scale Computing and Scalable AI to New Scientific Discovery

  3. Exploring the Exascale Universe

  4. Designing Scalable Vision Models for Scientific Understanding

  5. Morning Break

  6. Faster Scientific Multi-dimensional data analytics with NVIDIA cuPhoton

  7. AC-STRR: Training-Aware Visual Token Reduction for Scalable High-Resolution Medical Vision-Language Models

  8. Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging

  9. SkyMatch.jl: Fast, Differentiable Modeling for Millimeter-Sky Inference

  10. Characterizing Low-bit Deployment of 3D Medical Image Analysis on Portable AI Supercomputer

  11. Out-of-View Depth and Motion Prediction in Robotic Endoscopy

  12. Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model

  13. SuperSAM: Crafting a SAM Supernetwork via Structured Pruning and Unstructured Parameter Prioritization


Back to Workshop Archive Listing


The 1st International Workshop on Edge-Cloud-HPC Operational Continuum (ECHO)


  1. The 1st International Workshop on Edge-Cloud-HPC Operational Continuum (ECHO)

  2. Invited Talk

  3. How Much Can We Compress Field Images for Smart Agriculture?

  4. PerfDecode: Accelerating LLM Decoding on Systolic Arrays via Performance Modeling

  5. SPEAR: Semantic Partitioning and Edge-Adapted Routing for Distributed LLM Serving

  6. Morning Break

  7. VERA: Reinforcement Learning for Dynamic Memory Scaling of HPC Workloads in Kubernetes

  8. PRISM: Task-aware Slimming for Edge-Cloud LLMs

  9. Placing the Control Plane: Cloud-Native Federated Learning Across Batch-Scheduled HPC

  10. SplitFT: An Edge-Cloud Collaborative Federated Split Learning System for LLM Fine-Tuning

  11. Automated Task Placement for Hybrid HPC-Serverless Workflows

  12. Panel Discussion

  13. Closing Remarks


Back to Workshop Archive Listing


Eighth Workshop on Interactive and Urgent High Performance Computing


  1. Eighth Workshop on Interactive and Urgent High Performance Computing (WIUHPC)

  2. Invited talk: From Streaming Data to Timely Decisions: Infrastructure for Urgent Science

  3. From Idle to Urgent: A Resource-Harvested HPC Workflow for High-Fidelity Seismic Estimation

  4. Morning Break

  5. Lightning talks

  6. Panel: Security of Interactive and Urgent sessions in the era of hacking AIs

  7. Closing remarks


Back to Workshop Archive Listing




Back to SC26 Proceedings Archive