SC19 Proceedings

The International Conference for High Performance Computing, Networking, Storage, and Analysis

Computational Reproducibility at Exascale 2019 (CRE2019)


  1. Computational Reproducibility at Exascale 2019 (CRE2019)

  2. Reproducibility, Computability, and the Scientific Method

  3. Comparing Perturbation Models for Evaluating Stability of Post-Processing Pipelines in Neuroimaging

  4. Fast, Good, and Repeatable: Summations, Vectorization, and Reproducibility

  5. CRE2019 Morning Break

  6. Reproducibility and Provenance of James Webb Space Telescope Data Products

  7. Numerical Reproducibility Based on Minimal-Precision Validation

  8. Reproducibility and Variable Precision Computing

  9. Panel Discussion


Back to Workshop Archive Listing


Innovating the Network for Data Intensive Science (INDIS)


  1. Innovating the Network for Data Intensive Science (INDIS)

  2. SCinet DTN-as-a-Service Framework

  3. bwNetFlow: A Customizable Multi-Tenant Flow Processing Platform for Transit Providers

  4. INDIS Morning Break

  5. INDIS Showcases Panel: SCinet NRE, XNET and Architecture

  6. INDIS Keynote: The Relevance of Software Defined Exchange Points in the Path of Scientific Workflows

  7. Estimation of RTT and Loss Rate of Wide-Area Connections Using MPI Measurements

  8. INDIS Lunch Break

  9. Co-Scheduling of Advance and Immediate Bandwidth Reservations for Inter-Data Center Transfer

  10. INDIS Short Break

  11. Hop Recording and Forwarding State Logging: Two Implementations for Path Tracking in P4

  12. INDIS Afternoon Break

  13. G2: A Network Optimization Framework for High-Precision Analysis of Bottleneck and Flow Performance

  14. INDIS Keynote: Applications of ML and AI in Next Generation Wired and Wireless Networks

  15. Training Classifiers to Identify TCP Signatures in Scientific Workflows

  16. Sample Transfer Optimization with Adaptive Deep Neural Network

  17. INDIS Closing Remarks


Back to Workshop Archive Listing


Deep Learning on Supercomputers


  1. Deep Learning on Supercomputers

  2. Keynote: AI for HPC and HPC for AI: Bidirectional Convergence Efforts of HPC and AI on the Fugaku Supercomputer

  3. Deep Learning on Supercomputers Morning Break

  4. DeepDriveMD: Deep-Learning Driven Adaptive Molecular Simulations for Protein Folding

  5. Deep Facial Recognition Using Tensorflow

  6. Deep Learning Accelerated Light Source Experiments

  7. DC-S3GD: Delay-Compensated Stale-Synchronous SGD for Large-Scale Decentralized Neural Network Training

  8. Aggregating Local Storage for Scalable Deep Learning I/O

  9. Deep Learning on Supercomputers Lunch Break

  10. Highly-Scalable, Physics-Informed GANs for Learning Solutions of Stochastic PDEs

  11. Deep Learning for Gap Crossing Ability of Ground Vehicles

  12. Deep Learning on Supercomputers Afternoon Break

  13. Scaling Distributed Training of Flood-Filling Networks on HPC Infrastructure for Brain Mapping

  14. Evolving Larger Convolutional Layer Kernel Sizes for a Settlement Detection Deep-Learner on Summit

  15. Scaling TensorFlow, PyTorch, and MXNet Using MVAPICH2 for High-Performance Deep Learning on Frontera

  16. Strategies to Deploy and Scale Deep Learning on the Summit Supercomputer


Back to Workshop Archive Listing


Sixth SC Workshop on Best Practices for HPC Training and Education


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

  2. FreeCompilerCamp.org: Training for OpenMP Compiler Development from Cloud

  3. Introducing Novices to Scientific Parallel Computing

  4. Best Practices for HPC Training and Education Morning Break

  5. A Modular Course on Developing Research Software

  6. Teaching HPC Systems Administrators

  7. The Supercomputing Institute: A Systems-Focused Approach to HPC Training and Education

  8. Computational Mathematics, Science and Engineering (CMSE): Establishing an Academic Department Dedicated to Scientific Computation as a Discipline

  9. An Informal Introduction to HPC via a Numerical Weather Model and Low-Cost Hardware

  10. Computational Biology as a Compelling Pedagogical Tool in Computer Science Education

  11. Best Practices for HPC Training and Education Lunch Break

  12. Directed Internship and Apprenticeship toward a Sustainable HPC Workforce Development Pipeline

  13. Contributing HPC Skills to the HPC Certification Forum

  14. Creating a Relevant, Application-Based Curriculum for High Performance Computing in High School

  15. Self-Paced Learning in HPC Lab Courses

  16. Evaluating the Effectiveness of an Online Learning Platform in Transitioning from High Performance Computing to a Commercial Cloud Computing Environment

  17. Leveraging SC to Learn High-Performance Communication

  18. Best Practices for HPC Training and Education Afternoon Break

  19. Panel: Building the Future

  20. Open Discussion


Back to Workshop Archive Listing


The 5th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-5)


  1. The 5th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-5)

  2. DRBSD-5 Keynote Talk: Data Analysis through Advanced Scientific Computing Research at the Department of Energy

  3. Understanding Performance-Quality Trade-offs in Scientific Visualization Workflows with Lossy Compression

  4. DRBSD-5 Morning Break

  5. DRBSD-5 Invited Talk 1: Data Challenges for Nuclear Femtography

  6. A Collaborative Effort to Improve Lossy Compression Methods for Climate Data

  7. DRBSD-5 Invited Talk 2: Changing Science through Online Analysis

  8. PAVE: An In Situ Framework for Scientific Visualization and Machine Learning Coupling

  9. A Co-Design Study Of Fusion Whole Device Modeling Using Code Coupling

  10. DRBSD-5 Lunch Break

  11. DRBSD Keynote Talk 2: Data before Data in Fusion Science

  12. DRBSD-5 Invited Talk 3: Scientific Data at Exascale: Architecting Systems for Performance, Productivity, and Parallelism

  13. DRBSD-5 Afternoon Break

  14. DRBSD-5 Invited Talk 4: High Performance Computing at BP

  15. DRBSD-5 Invited Talk: In Situ Data Analytics for Next Generation Molecular Dynamics Workflows

  16. Analyzing the Performance and Accuracy of Lossy Checkpointing on Sub-Iteration of NWChem

  17. Using Machine Learning to Reduce Ensembles of Geological Models for Oil and Gas Exploration

  18. Exploring Lossy Compression of Gene Expression Matrices


Back to Workshop Archive Listing


Parallel Applications Workshop, Alternatives to MPI+X


  1. Parallel Applications Workshop, Alternatives to MPI+X

  2. Computer Science Challenges to Imaging the Universe with the SKA Radio-Telescope

  3. PAW-ATM Morning Break

  4. Soleil-X: Turbulence, Particles, and Radiation in the Regent Programming Language

  5. Exploring the Use of Novel Programming Models in Land Surface Models

  6. Simulating Ultralight Dark Matter with Chapel : An Experience Report

  7. A UPC++ Actor Library and Its Evaluation On a Shallow Water Proxy Application

  8. Evaluation of Programming Models to Address Load Imbalance on Distributed Multi-Core CPUs: A Case Study with Block Low-Rank Factorization

  9. Scalable Machine Learning with OpenSHMEM

  10. PAW-ATM Lunch Break

  11. Designing, Implementing, and Evaluating the Upcoming OpenSHMEM Teams API

  12. Enabling Low-Overhead Communication in Multi-Threaded OpenSHMEM Applications Using Contexts

  13. Efficient Active Message RMA in GASNet Using a Target-Side Reassembly Protocol

  14. PAW-ATM Afternoon Break

  15. Pygion: Flexible, Scalable Task-Based Parallelism with Python

  16. Arkouda: NumPy-Like Arrays at Massive Scale Backed by Chapel

  17. Panel Discussion: Applications in Alternatives to MPI+X


Back to Workshop Archive Listing


Women in HPC: Diversifying the HPC Community and Engaging Male Allies


  1. Women in HPC: Diversifying the HPC Community and Engaging Male Allies

  2. Keynote: The Butterfly Effect of Inclusive Leadership

  3. Women in HPC Morning Break

  4. Thriving at Workplace (Short Talks)

  5. Panel Discussion: Engaging Male Allies

  6. Women in HPC Lunch Break

  7. Early/Mid Career Lightning Talks Session

  8. Women in HPC Afternoon Break

  9. Panel Discussion: Mentoring: Why We Need It, Best Practice, and the Business Case for Great Mentoring Programs

  10. Women-in-HPC Workshop Closing


Back to Workshop Archive Listing


Workshop on Exascale MPI (ExaMPI)


  1. Workshop on Exascale MPI (ExaMPI)

  2. ExaMPI Keynote

  3. ExaMPI Morning Break

  4. Multirate: A Flexible MPI Benchmark for Fast Assessment of Multithreaded Communication Performance

  5. Impacts of Multi-GPU MPI Collective Communications on Large FFT Computation

  6. Node-Aware Improvements to Allreduce

  7. Accelerating the Global Arrays ComEx Runtime Using Multiple Progress Ranks

  8. ExaMPI Lunch Break

  9. RDMA-Based Library for Collective Operations in MPI

  10. Using MPI-3 RMA for Active Messages

  11. ExaMPI Afternoon Break

  12. ExaMPI Invited Talk #1 - Evaluating MPI Message Size Summary Statistics

  13. ExaMPi Invited Talk #2 - The Case for Modular Generalizable Proxy Applications for Systems Software Research

  14. ExaMPI Vendor Panel - MPI for Exascale: Challenges and Opportunities


Back to Workshop Archive Listing


H2RC 2019: Fifth International Workshop on Heterogeneous High-Performance Reconfigurable Computing


  1. H2RC 2019: Fifth International Workshop on Heterogeneous High-Performance Reconfigurable Computing

  2. SYCL: A Single-Source C++ Standard for Heterogeneous Computing

  3. hlslib: Software Engineering for Hardware Design

  4. Morning Coffee Break

  5. 2GRVI Phalanx: A 1332-Core RISC-V RV64I Processor Cluster Array with an HBM2 High Bandwidth Memory System, and an OpenCL-like Programming Model, in a Xilinx VU37P FPGA [WIP Report]

  6. CFD Acceleration with FPGA

  7. Data Flow Pipes: A SYCL Extension for Spatial Architectures

  8. Morning 5-Minute Break

  9. It's All about Data Movement: Optimizing FPGA Data Access to Boost Performance

  10. The Memory Controller Wall: Benchmarking the Intel FPGA SDK for OpenCL Memory Interface

  11. Accelerating Large Garbled Circuits on an FPGA-Enabled Cloud

  12. H2RC'19 Lunch Break

  13. ML Acceleration with Heterogeneous Computing for Big Data Physics Experiments

  14. Testbed for the Research Community Exploring Next-Generation Cloud Platforms

  15. Afternoon Break

  16. High-Throughput Multi-Threaded Sum-Product Network Inference in the Reconfigurable Cloud

  17. Implementation and Impact of an Ultra-Compact Multi-FPGA Board for Large System Prototyping

  18. Afternoon 5-Minute Break

  19. FBLAS: Streaming Linear Algebra Kernels on FPGA

  20. Combining Perfect Shuffle and Bitonic Networks for Efficient Quantum Sorting

  21. Performance and Energy Efficiency Analysis of Reverse Time Migration on a FPGA Platform


Back to Workshop Archive Listing


Workshop on Education for High Performance Computing (EduHPC)


  1. Welcome: Workshop on Education for High Performance Computing (EduHPC)

  2. Keynote: Preparing HPC Education for a Post-Moore Future

  3. Morning Break

  4. Paper Session A (Session Chair: Alexandru Iosup)

  5. Teaching Parallel and Distributed Computing Concepts in Simulation with WRENCH

  6. A Gentle Introduction to Heterogeneous Computing for CS1 Students

  7. Assessing the Integration of Parallel and Distributed Computing in Early Undergraduate Computer Science Curriculum Using Unplugged Activities

  8. Paper Session A: Discussions

  9. Lightning Talk Session (Session Chair: Trilce Estrada)

  10. The Data Science Journal Club

  11. Excellence in Computer Engineering Education (EXCEED): Integrating PDC Topics in the ECE Courses at UIUC

  12. Building a Data Science Education Ecosystem Resource Collection

  13. Increasing Undergraduate Research in Computational Sciences

  14. Teaching and Advising HPC at NTNU

  15. A Jupyter Notebook Based Tool for Building Skills in Computational Statistical Mechanics

  16. Hearing Program Behavior with TSAL

  17. Parallelism for Beginners with Fun Examples

  18. Actionable Guidance for Fresh HPC Researchers

  19. Lightning Talk Discussions

  20. Lunch Break

  21. IEEE TCPP Curriculum on Parallel and Distributed Computing - an Update

  22. Paper Session B (Session Chair: Katharine Cahill)

  23. Teaching on Demand: an HPC Experience

  24. Successful Systems in Production Graduate Teaching

  25. Paper Session B: Discussions

  26. Afternoon Break

  27. Paper Session C (Session Chair: Joel Adams)

  28. Teaching Concurrent and Distributed Programming With Concepts Over Mathematical Proofs

  29. Measuring the Impact of HPC Training

  30. Toward Improving Collaborative Behavior During Competitive Programming Assignments

  31. Paper Session C: Discussions

  32. Peachy Parallel Assignment Session (Session Chair: David Bunde)

  33. Agent-Based Simulation of Fire Extinguishing: an Assignment for OpenMP, MPI, and CUDA/OpenCL

  34. Thread-to-Core Optimization Problem

  35. Parallel Computing in the Cloud for All Levels

  36. Introducing Parallel Prefix-Sums Algorithm and Its Applications in an Undergraduate Course

  37. Pin Finder

  38. Dask Processing and Analytics for Large Datasets

  39. Peachy Parallel Assignment Discussions

  40. Best Paper Announcement and Closing Remarks


Back to Workshop Archive Listing


Workshop on Programming and Performance Visualization Tools (ProTools)


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

  2. Keynote

  3. ProTools Morning Break

  4. Understanding the Performance of GPGPU Applications from a Data-Centric View

  5. Asvie: A Timing-Agnostic SVE Optimization Methodology

  6. Designing Efficient Parallel Software via Compositional Performance Modeling

  7. Performance Analysis of Tile Low-Rank Cholesky Factorization Using PaRSEC Instrumentation Tools

  8. ProTools Lunch Break

  9. The Case for a Common Instrumentation Interface for HPC Codes

  10. Keynote / Panel

  11. ProTools Afternoon Break

  12. Automatic Instrumentation Refinement for Empirical Performance Modeling

  13. Multi-Level Performance Instrumentation for Kokkos Applications Using TAU

  14. CHAMPVis: Comparative Hierarchical Analysis of Microarchitectural Performance

  15. In Situ Visualization of Performance Metrics in Multiple Domains

  16. Toward a Programmable Analysis and Visualization Framework for Interactive Performance Analytics


Back to Workshop Archive Listing


The 14th Workshop on Workflows in Support of Large-Scale Science (WORKS19)


  1. The 14th Workshop on Workflows in Support of Large-Scale Science (WORKS19)

  2. WORKS19 Welcome

  3. WORKS19 Keynote: Priority Research Directions for In Situ Data Management: Enabling Scientific Discovery from Diverse Data Sources

  4. WORKS19 Morning Break

  5. Provenance Data in the Machine Learning Lifecycle in Computational Science and Engineering

  6. A Codesign Framework for Online Data Analysis and Reduction

  7. Top-Down Performance Analysis Methodology for Workflows: Tracking Performance Issues from Overview to Individual Operations

  8. Data-Aware and Simulation-Driven Planning of Scientific Workflows on IaaS Clouds

  9. Exploration of Workflow Management Systems Emerging Features from Users' Perspectives

  10. WORKS19 Lunch Break

  11. Incorporating Scientific Workflows in Computing Research Processes

  12. Comparing GPU Power and Frequency Capping: A Case Study with the MuMMI Workflow

  13. WORKS19 Afternoon Break

  14. Inter-Job Scheduling for High-Throughput Material Screening Applications

  15. Empowering Agroecosystem Modeling with HTC Scientific Workflows: The Cycles Model Use Case

  16. A Performance Comparison of Dask and Apache Spark for Data-Intensive Neuroimaging Pipelines

  17. On a Parallel Spark Workflow for Frequent Itemset Mining Based on Array Prefix-Tree

  18. WORKS19 Panel


Back to Workshop Archive Listing


The 2019 International Workshop on Software Engineering for HPC-Enabled Research (SE-HER 2019)


  1. The 2019 International Workshop on Software Engineering for HPC-Enabled Research (SE-HER 2019)

  2. Software Engineering Practices and Related Challenges in the LSST Dark Energy Science Collaboration

  3. A Study of Hydrodynamics Based Community Codes in the Astrophysics

  4. Large Group Discussion

  5. SE-HER 2019 Morning Break

  6. Ice Breaking Exercise

  7. Lightweight Software Process Improvement Using Productivity and Sustainability Improvement Planning (PSIP)

  8. Small Group Discussion

  9. Large Group Report Out

  10. SE-HER 2019 Lunch Break

  11. Role Oriented Code Generation in an Engine for Solving Hyperbolic PDE Systems

  12. FQL: An Extensible Feature Query Language and Toolkit on Searching Software Characteristics for HPC Applications

  13. Presenting Information about Software in JOSS: Current and Potential Practices

  14. Small Group Discussion

  15. SE-HER 2019 Afternoon Break

  16. Further Small Group Discussions

  17. Large Group Report Out

  18. Final Discussion


Back to Workshop Archive Listing


Fifth Computational Approaches for Cancer Workshop (CAFCW19)


  1. Fifth Computational Approaches for Cancer Workshop (CAFCW19)

  2. Welcome - Fifth Computational Approaches for Cancer

  3. Keynote: Fifth Computational Approaches for Cancer

  4. CAFCW19 Morning Break

  5. Integrating High-Performance Simulations and Learning toward Improved Cancer Therapy

  6. Machine Learning Algorithms in Histology and Radiology for Cancer Drug Discovery and Development

  7. A Scalable, Validated Platform for Generative Lead Optimization of De Novo Molecules: Case Study in Discovery of Potent, Selective Aurora Kinase Inhibitors with Favorable Secondary Pharmacology

  8. Deep Learning Enabled Unsupervised State Identification in KRAS Dimers and Interacting Lipids

  9. Fusion of Structure Based Deep Learning to Accelerate Molecular Docking Predictions

  10. Panel: AI and Cancer Drug Discovery

  11. CAFCW19 Lunch Break

  12. CAFCW19: Afternoon Welcome

  13. Machine Learning Directed Multiscale Simulations To Explore RAS Biology

  14. Semi-Supervised Method for Countering Batch Effect

  15. Acceleration of Hyperparameter Optimization via Task Parallelism for Information Extraction from Cancer Pathology Reports

  16. CAFCW19 Afternoon Break

  17. Digital Twins for Predictive Cancer Care: an HPC-Enabled Community Initiative

  18. Deep Kernel Learning for Information Extraction from Cancer Pathology Reports

  19. Massively Parallel Large-Scale Multi-Model Simulation of Tumor Development including Treatments

  20. Panel Session: Collaborations, Community, and Computational Approaches for Cancer

  21. CAFCW19 Wrap-Up


Back to Workshop Archive Listing


HPC for Urgent Decision Making (UrgentHPC)


  1. HPC for Urgent Decision Making (UrgentHPC)

  2. Keynote: Wildfire Risk Modeling, Simulating at the Gazillion Scale

  3. Quantifying Uncertainty in Source Term Estimation with Tensorflow Probability

  4. Statistical Parameter Selection for Clustering Persistence Diagrams

  5. UrgentHPC Afternoon Break

  6. On-Demand Urgent High Performance Computing Utilizing the Google Cloud Platform

  7. The Technologies Required for Fusing HPC and Real-Time Data to Support Urgent Computing

  8. An Interactive Data-Driven HPC System for Forecasting Weather, Wildland Fire, and Smoke

  9. Urgent Tsunami Computing

  10. Panel: What Role Can HPC Play in Urgent Decision Making?


Back to Workshop Archive Listing


Third Workshop on Interactive High Performance Computing


  1. Third Workshop on Interactive High Performance Computing

  2. Accelerating Experimental Science Using Jupyter and NERSC HPC

  3. Interactive Supercomputing for Experimental Data-Driven Workflows

  4. Interactive High Performance Computing Morning Break

  5. Portals for Interactive Steering of HPC Workflows

  6. Pangeo Ecosystem, Interactive Computing Tools for Geosciences: Benchmark on HPC

  7. Interactivity Use Case Panel Discussion

  8. Interactive High Performance Computing Closing Remarks


Back to Workshop Archive Listing


6th International Workshop on HPC User Support Tools (HUST-19)


  1. 6th International Workshop on HPC User Support Tools (HUST-19)

  2. Buildtest: A Software Testing Framework with Module Operations for HPC systems

  3. Using Malleable Task Scheduling to Accelerate Package Manager Installations

  4. HUST-19 Morning Break

  5. Enabling Continuous Testing of HPC Systems Using ReFrame

  6. Tools for Monitoring CPU Usage and Affinity in Multicore Supercomputers

  7. HUST19 Panel: HPC User Tickets Discussion


Back to Workshop Archive Listing


SuperCompCloud: Workshop on Interoperability of Supercomputing and Cloud Technologies


  1. SuperCompCloud: Workshop on Interoperability of Supercomputing and Cloud Technologies

  2. Scalability and Data Security: Deep Learning with Health Data on Future HPC Platforms

  3. Cloud and Supercomputing Platforms at NCI Australia: the Why, the How, and the Future.

  4. SuperCompCloud Morning Break

  5. HPC and Cloud Operations at CERN

  6. Computing Without Borders: Combining Cloud and HPC to Advance Experimental Science.

  7. OpenStack and the Software-Defined Supercomputer

  8. Perform Like a Supercomputer, Run Like a Cloud

  9. SuperCompCloud Workshop Q&A Panel and Closing


Back to Workshop Archive Listing


MCHPC’19: Workshop on Memory Centric High Performance Computing


  1. Opening -- MCHPC’19: Workshop on Memory Centric High Performance Computing

  2. MCHPC’19 Keynote Talk: Prospects for Memory

  3. MCHPC'19 Morning Break

  4. Performance Evaluation of the Intel Optane DC Memory With Scientific Benchmarks

  5. Optimizing Data Layouts for Irregular Applications on a Migratory Thread Architecture

  6. Optimizing Post-Copy Live Migration with System-Level Checkpoint Using Fabric-Attached Memory

  7. Optimizing Memory Layout of Hyperplane Ordering for Vector Supercomputer SX-Aurora TSUBASA

  8. Generalized Sparse Matrix-Matrix Multiplication for Vector Engines and Graph Applications

  9. A Distributed Deep Memory Hierarchy System for Content-based Image Retrieval of Big Whole Slide Image Datasets

  10. MCHPC'19 Lunch Break

  11. Performance Evaluation of Advanced Features in CUDA Unified Memory

  12. Explicit Data Layout Management for Autotuning Exploration on Complex Memory Topologies

  13. Machine Learning Guided Optimal Use of GPU Unified Memory

  14. MCHPC'19 Afternoon Break

  15. UMap: Enabling Application-driven Optimizations for Page Management

  16. Extending OpenMP map Clause to Bridge Storage and Device Memory

  17. MCHPC’19 Panel: Software and Hardware Support for Programming Heterogeneous Memory


Back to Workshop Archive Listing


Machine Learning in HPC Environments


  1. Machine Learning in HPC Environments

  2. Opening Remarks: Machine Learning in HPC Environments

  3. Morning Keynote : HPC for ML and ML for HPC - scalability, communication, and programming

  4. Machine Learning in HPC Environments Morning Break

  5. Understanding Scalability and Fine-Grain Parallelism of Synchronous Data Parallel Training

  6. Fine-Grained Exploitation of Mixed Precision for Faster CNN Training

  7. Metaoptimization on a Distributed System for Deep Reinforcement Learning

  8. Scheduling Optimization of Parallel Linear Algebra Algorithms Using Supervised Learning

  9. Machine Learning in HPC Environments Lunch Break

  10. Parallel Data-Local Training for Optimizing Word2Vec Embeddings for Word and Graph Embeddings

  11. Scalable Hyperparameter Optimization with Lazy Gaussian Processes

  12. Machine Learning in HPC Environments Afternoon Break

  13. Afternoon Keynote - Running large models in minutes: an engineering journey through high performance for AI

  14. GradVis: Visualization and Second Order Analysis of Optimization Surfaces During the Training of Deep Neural Networks

  15. DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems

  16. Concluding Remarks - Machine Learning in HPC Environment


Back to Workshop Archive Listing


IA^3 2019: 9th Workshop on Irregular Applications: Architectures and Algorithms


  1. IA^3 2019: 9th Workshop on Irregular Applications: Architectures and Algorithms

  2. Keynote 1

  3. IA^3 2019 Morning Break

  4. Conveyors for Streaming Many-to-Many Communication

  5. Extending a Work-Stealing Framework with Priorities and Weights

  6. RDMA vs. RPC for Implementing Distributed Data Structures

  7. A Mixed Precision Multicolor Point-Implicit Solver for Unstructured Grids on GPUs

  8. Mixed-Precision Tomographic Reconstructor Computations on Hardware Accelerators

  9. Metall: A Persistent Memory Allocator Enabling Graph Processing

  10. IA^3 2019 Lunch Break

  11. Keynote 2: Sparse Linear Algebra in Facebook's Deep Learning Models

  12. iPregel: Strategies to Deal with an Extreme Form of Irregularity in Vertex-Centric Graph Processing

  13. IA^3 2019 Afternoon Break

  14. Stretching Jacobi: A Two-Stage Pivoting Approach for Block-Based Factorization

  15. A Hardware Prefetching Mechanism for Vector Gather Instructions

  16. Performance Impact of Memory Channels on Sparse and Irregular Algorithms

  17. Cascaded DMA Controller for Speedup of Indirect Memory Access in Irregular Applications

  18. Debate


Back to Workshop Archive Listing


Tenth Annual Workshop for the Energy Efficient HPC Working Group


  1. Tenth Annual Workshop for the Energy Efficient HPC Working Group

  2. Keynote: 30 Year Perspective on HPC and Energy Efficiency

  3. EE HPC WG Morning Break

  4. State of the Working Group

  5. The Power Grid

  6. Novel Cooling Technologies and Experiences

  7. EE HPC WG Lunch Break

  8. Machine Installations - Pre-Exascale and Beyond

  9. EE HPC WG Afternoon Break

  10. Silicon Manufacturing Variability

  11. Operational Data Analytics - Global Survey Results

  12. Panel: Challenges with Manufacturing Variation and Other Challenges to Platform Level Monitoring and Management

  13. Closing Remarks


Back to Workshop Archive Listing


International Parallel Data Systems Workshop (PDSW)


  1. International Parallel Data Systems Workshop (PDSW)

  2. Alluxio - Data Orchestration for Analytics and AI in the Cloud

  3. PDSW Morning Break

  4. In Search of a Fast and Efficient Serverless DAG Engine

  5. Enabling Transparent Asynchronous I/O Using Background Threads

  6. PDSW Works in Progress I

  7. Active Learning-Based Automatic Tuning and Prediction of Parallel I/O Performance

  8. Applying Machine Learning to Understand the Write Performance of Large-Scale Parallel Filesystems

  9. PDSW Lunch Break

  10. A House Divided: Why Don't Cloud Storage and HPC Storage Share More Technology?

  11. PDSW Works in Progress II

  12. PDSW Afternoon Break

  13. Towards Physical Design Management in Storage Systems

  14. A Foundation for Automated Placement of Data

  15. Profiling Platform Storage Using IO500 and Mistral

  16. Understanding Data Motion in the Modern HPC Data Center

  17. PDSW Works in Progress III


Back to Workshop Archive Listing


The 10th International Workshop on Performance Modeling, Benchmarking, and Simulation of High-Performance Computer Systems (PMBS19)


  1. The 10th International Workshop on Performance Modeling, Benchmarking, and Simulation of High-Performance Computer Systems (PMBS19)

  2. Automatic Throughput and Critical Path Analysis of x86 and ARM Assembly Kernels

  3. An Instruction Roofline Model for GPUs

  4. PMBS19 Morning Break

  5. Exploiting Hardware-Accelerated Ray Tracing for Monte Carlo Particle Transport with OpenMC

  6. Enhancing Monte Carlo Proxy Applications on GPUs

  7. Comparing Managed Memory and UVM with and without Prefetching on NVIDIA Volta GPUs

  8. Testing the Limits of Tapered Fat Tree Networks

  9. Validation of the gem5 Simulator for x86 Architectures

  10. PMBS19 Lunch Break

  11. A Generalized Statistics-Based Model for Predicting Network-Induced Variability

  12. CUDA Flux: A Lightweight Instruction Profiler for CUDA Applications

  13. PMBS19 Afternoon Break

  14. OMB-UM: Design, Implementation, and Evaluation of CUDA Unified Memory Aware MPI Benchmarks

  15. Fine-Grained Analysis of Communication Similarity between Real and Proxy Applications

  16. Performance Analysis of Deep Learning Workloads on Leading-Edge Systems


Back to Workshop Archive Listing


10th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems


  1. 10th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems

  2. Keynote 1: Exascale Application Progress and Challenges

  3. Morning Break

  4. Keynote 2: Toward Scaling Deep Learning to 100,000 Processors - The Fugaku Challenge

  5. GPU Acceleration of Communication Avoiding Chebyshev Basis Conjugate Gradient Solver for Multiphase CFD Simulations

  6. Optimization of a Solver for Computational Materials and Structures Problems on NVIDIA Volta and AMD Instinct GPUs

  7. Toward Half-Precision Computation for Complex Matrices: A Case Study for Mixed Precision Solvers on GPUs

  8. Lunch Break

  9. Keynote 3: The Extreme-Scale Scientific Software Stack and Its Promise for the Exascale Computing Era

  10. Afternoon Break

  11. Extreme Scale Phase-Field Simulation of Sintering Processes

  12. Generic Matrix Multiplication for Multi-GPU Accelerated Distributed-Memory Platforms Over PaRSEC

  13. Toward Accelerated Unstructured Mesh Particle-in-Cell

  14. Parallel Multigrid Methods on Manycore Clusters with IHK/McKernel

  15. Making Speculative Scheduling Robust to Incomplete Data

  16. Parallel SFC-Based Mesh Partitioning and Load Balancing


Back to Workshop Archive Listing


Sixth Workshop on Accelerator Programming Using Directives (WACCPD)


  1. Sixth Workshop on Accelerator Programming Using Directives (WACCPD)

  2. WACCPD Opening Remarks

  3. Keynote: Perlmutter - A 2020 Pre-Exascale GPU-Accelerated System for NERSC: Architecture and Application Performance Optimization

  4. WACCPD Morning Break

  5. GPU Implementation of a Sophisticated Implicit Low-Order Finite Element Solver with FP21-32-64 Computation Using OpenACC

  6. Acceleration in Acoustic Wave Propagation Modeling Using OpenACC/OpenMP and Its Hybrid for the Global Monitoring System

  7. Accelerating the Performance of Modal Aerosol Module of E3SM Using OpenACC

  8. Evaluation of Directive-Based GPU Programming Models on a Block Eigensolver with Consideration of Large Sparse Matrices

  9. WACCPD Lunch Break

  10. Invited Talk: The SPEC ACCEL Benchmark – Results and Lessons Learned

  11. Performance of the RI-MP2 Fortran Kernel of GAMESS on GPUs via Directive-Based Offloading with Math Libraries

  12. WACCPD Afternoon Break

  13. Performance Portable Implementation of a Kinetic Plasma Simulation Mini-App

  14. A Portable SIMD Primitive Using Kokkos for Heterogeneous Architectures

  15. WACCPD Best Paper Award

  16. Panel: Convergence, Divergence, or New Approaches? - The Future of Software-Based Abstractions for Heterogeneous Supercomputing

  17. WACCPD Closing Remarks


Back to Workshop Archive Listing


ISAV 2019: In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization


  1. ISAV 2019: In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization

  2. In-Situ Visualization for the Large Scale Computing Initiative Milestone

  3. A New Approach for In Situ Analysis in Fully Coupled Earth System Models

  4. In Situ Adaptive Timestep Control and Visualization Based on the Spatio-Temporal Variations of the Simulation Results

  5. ISAV 2019 Morning Break

  6. The Impact of Work Distribution on In Situ Visualization: A Case Study

  7. The Challenges of Elastic In Situ Analysis and Visualization

  8. In Situ Particle Advection Via Parallelizing Over Particles

  9. Spack Meets Singularity: Creating Movable In-Situ Analysis Stacks with Ease

  10. HDF5 as a Vehicle for In Transit Data Movement

  11. In Situ and In Transit Visualization for Numerical Simulations in HPC

  12. Metadata Enabled Optimized Partitioning for M to N In Transit Processing with SENSEI

  13. In Situ Visualization and Analysis Workflows for WarpX

  14. In Transit Management and Creation of Data Extracts

  15. Lightning Talks Q&A

  16. ISAV 2019 Lunch Break

  17. Keynote Talk: In-Situ Analysis for Extreme-Scale Cosmological Simulations

  18. ISAV 2019 Afternoon Break

  19. Interactive In Situ Visualization and Analysis Using Ascent and Jupyter

  20. Invited Presentation: Enabling Scientific Discovery from Diverse Data Sources through In Situ Data Management

  21. The ISAV 2019 UnPanel

  22. Closing Remarks


Back to Workshop Archive Listing


PHOTONICS: Photonics-Optics Technology Oriented Networking, Information, and Computing Systems


  1. Keynote - Silicon Photonics: Technology Advancement and Applications

  2. Morning Break

  3. Shrinking Photonic Interconnection Networks from Kilometers to Millimeters

  4. HPC Interconnects at the End of Moore’s Law

  5. Past, Current and Future Technologies for Optical Submarine Cables

  6. Simulation-Driven Design of Photonic Quantum Communication Networks

  7. Overview of Silicon Photonics Components for Commercial DWDM Applications

  8. An Approximate Thermal-Aware Q-Routing for Optical NoCs

  9. On the Feasibility of Optical Circuit Switching for Distributed Deep Learning

  10. Lunch Break

  11. Photonic Switching and Computing are Coming

  12. High-Radix Sub-Microsecond Photonic Switch on a Chip

  13. Sub-Microsecond Optical Circuit Switched Networks for Data Centers and HPCs

  14. Low-Cost High-Radix Photonic Switch for Rack-Scale Computing Systems

  15. Afternoon Break

  16. Using the Optical Processing Unit for Large-Scale Machine Learning

  17. An Optical Neural Network Architecture Based on Highly Parallelized WDM-Multiplier-Accumulator

  18. Ising Machine: an Approach to Solve Combinational Optimization Problems

  19. Panel: Rejuvenate Post-Moore's Law Information Systems with Photonics


Back to Workshop Archive Listing


3nd International Workshop on Software Correctness for HPC Applications (Correctness 2019)


  1. 3nd International Workshop on Software Correctness for HPC Applications (Correctness 2019)

  2. Reasoning about Floating Point in the Real World

  3. Correctness 2019 Morning Break

  4. Debugging and Optimization of HPC Programs with the Verrou Tool

  5. Exploring Regression of Data Race Detection Tools Using DataRaceBench

  6. Toward Multi-Precision, Multi-Format Numerics

  7. Tool Integration for Source-Level Mixed Precision

  8. Correctness 2019 Lunch Break

  9. Contained Chaos: Quality Assurance for the Community Earth System Model

  10. Correctness 2019 Afternoon Break

  11. Taming the Digital Wild West: Using Domain Specific Languages to Enforce Correctness Properties in Data Science, Machine Learning, and Scientific Modeling

  12. Bounded Verification of Sparse Matrix Computations

  13. Investigating the Impact of Mixed Precision on Correctness for a Large Climate Code


Back to Workshop Archive Listing


1st Annual Workshop on Large-Scale Experiment-in-the-Loop-Computing (XLOOP)


  1. 1st Annual Workshop on Large-Scale Experiment-in-the-Loop-Computing (XLOOP)

  2. Computational Strategies to Increase Efficiency of Gaussian-Process-Driven Autonomous Experiments

  3. Scientific Image Restoration Anywhere

  4. XLOOP Afternoon Break

  5. Distributed Global Digital Volume Correlation by Optimal Transport

  6. Sparse Data Management in HDF5

  7. Data Processing at the Linac Coherent Light Source

  8. Balsam: Near Real-Time Experimental Data Analysis on Supercomputers

  9. XLOOP Panel: Big Science, Big Computing

  10. XLOOP Awards and Conclusion


Back to Workshop Archive Listing


Containers and New Orchestration Paradigms for Isolated Environments in HPC (CANOPIE HPC)


  1. Containers and New Orchestration Paradigms for Isolated Environments in HPC (CANOPIE HPC)

  2. Evaluation and Benchmarking of Singularity MPI Containers on EU Research e-Infrastructure

  3. Enabling HPC workloads on Cloud Infrastructure Using Kubernetes Container Orchestration Mechanisms

  4. CANOPIE HPC Afternoon Break

  5. Long-Term Preservation of Repeatable Builds in Occam

  6. KBase: A Platform for Reproducible Bioinformatics Research

  7. HPC Container Runtimes Have Minimal or No Performance Impact

  8. On-Node Resource Manager for Containerized HPC Workloads

  9. A Case for Portability and Reproducibility of HPC Containers

  10. Lightning Session - CANOPIE-HPC


Back to Workshop Archive Listing


2nd International Workshop on Performance, Portability, and Productivity in HPC (P3HPC)


  1. 2nd International Workshop on Performance, Portability, and Productivity in HPC (P3HPC)

  2. Opening Remarks

  3. Performance Portability Across Diverse Computer Architectures

  4. Performance Portability of a Wilson Dslash Stencil Operator Mini-App Using Kokkos and SYCL

  5. Performance Portability of Multi-Material Kernels

  6. An Approach for Indirectly Adopting a Performance Portability Layer in Large Legacy Codes

  7. Panel Discussion - Application Perspectives

  8. P3HPC Morning Break

  9. On Applying Performance Portability Metrics

  10. mdspan in C++: A Case Study in the Integration of Performance Portable Features into International Language Standards

  11. RAJA: Portable Performance for Large-Scale Scientific Applications

  12. ClangJIT: Enhancing C++ with Just-in-Time Compilation

  13. Panel Session - P3 Enabling Technology

  14. Closing Remarks


Back to Workshop Archive Listing


HPC Systems Professionals Workshop (HPCSYSPROS19)


  1. HPC Systems Professionals Workshop (HPCSYSPROS19)

  2. Chameleon: How to Build a Cloud++

  3. Decoupling OpenHPC Critical Services

  4. Implementing a Common HPC Environment in a Multi-User Spack Instance

  5. HPCSYSPROS19 Morning Break

  6. Arbiter: Dynamically Limiting Resource Consumption on Login Nodes

  7. Using GUFI in Data Management

  8. Monitoring HPC Services with CheckMK

  9. The Road to Devops HPC Cluster Management

  10. What Deploying MFA Taught Us about Changing Infrastructure

  11. A Better Way of Scheduling Jobs on HPC Systems: Simultaneous Fair-Share

  12. Closing Remarks and Open Discussion


Back to Workshop Archive Listing


The 3rd Industry/University Joint International Workshop on Data-Center Automation, Analytics, and Control (DAAC)


  1. The 3rd Industry/University Joint International Workshop on Data-Center Automation, Analytics, and Control (DAAC)

  2. CloudTraceViz: A Visualization Tool for Tracing Dynamic Usage of Cloud Computing Resources

  3. MetricQ: A Scalable Infrastructure for Processing High-Resolution Time Series Data

  4. MELA: A Visual Analytics Tool for Studying Multifidelity HPC System Logs

  5. Job Outcome Prediction via Text Log Analysis

  6. HiperJobViz: Visualizing Resource Allocations in High-Performance Computing Center via Multivariate Health-Status Data

  7. DAAC Morning Break

  8. Multi-Source Cooling Control Algorithm

  9. HyperOXN: A Novel Optical Cross-Connect Architecture for Data Centers

  10. DAAC Industrial/University Joint Panel Discussion


Back to Workshop Archive Listing