1st Edition

High Performance Visualization Enabling Extreme-Scale Scientific Insight

Edited By E. Wes Bethel, Hank Childs, Charles Hansen Copyright 2013
    516 Pages 142 B/W Illustrations
    by Chapman & Hall

    516 Pages 142 B/W Illustrations
    by Chapman & Hall

    Visualization and analysis tools, techniques, and algorithms have undergone a rapid evolution in recent decades to accommodate explosive growth in data size and complexity and to exploit emerging multi- and many-core computational platforms. High Performance Visualization: Enabling Extreme-Scale Scientific Insight focuses on the subset of scientific visualization concerned with algorithm design, implementation, and optimization for use on today’s largest computational platforms.

    The book collects some of the most seminal work in the field, including algorithms and implementations running at the highest levels of concurrency and used by scientific researchers worldwide. After introducing the fundamental concepts of parallel visualization, the book explores approaches to accelerate visualization and analysis operations on high performance computing platforms. Looking to the future and anticipating changes to computational platforms in the transition from the petascale to exascale regime, it presents the main research challenges and describes several contemporary, high performance visualization implementations.

    Reflecting major concepts in high performance visualization, this book unifies a large and diverse body of computer science research, development, and practical applications. It describes the state of the art at the intersection of scientific visualization, large data, and high performance computing trends, giving readers the foundation to apply the concepts and carry out future research in this area.

    Introduction, E. Wes Bethel
    Historical Perspective
    Moore's Law and the Data Tsunami
    Focus of this Book
    Book Organization and Themes
    Conclusion

    I Distributed Memory Parallel Concepts and Systems
    Parallel Visualization Frameworks
    , Hank Childs
    Introduction
    Background
    Parallelization Strategy
    Usage
    Advanced Processing Techniques
    Conclusion

    Remote and Distributed Visualization Architectures, E. Wes Bethel and Mark Miller
    Introduction
    Visualization Performance Fundamentals and Networks
    The Send-Images Partitioning
    The Send-Data Partitioning
    The Send-Geometry Partitioning
    Hybrid and Adaptive Approaches
    Which Pipeline Partitioning Works the Best?
    Case Study: Visapult
    Case Study: Chromium Renderserver
    Case Study: VisIt and Dynamic Pipeline Reconfiguration
    Conclusion

    Rendering, Charles Hansen, E. Wes Bethel, Thiago Ize, and Carson Brownlee
    Introduction
    Rendering Taxonomy
    Rendering Geometry
    Volume Rendering
    Real-Time Ray Tracer for Visualization on a Cluster
    Conclusion

    Parallel Image Compositing Methods, Tom Peterka and Kwan-Liu Ma
    Introduction
    Basic Concepts and Early Work in Compositing
    Recent Advances
    Results
    Discussion and Conclusion

    Parallel Integral Curves, David Pugmire, Tom Peterka, and Christoph Garth
    Introduction
    Challenges to Parallelization
    Approaches to Parallelization
    Conclusion

    II Advanced Processing Techniques
    Query-Driven Visualization and Analysis,
    Oliver Rübel, E. Wes Bethel, Prabhat, and Kesheng Wu
    Introduction
    Data Subsetting and Performance
    Formulating Multivariate Queries
    Applications of Query-Driven Visualization
    Conclusion

    Progressive Data Access for Regular Grids, John Clyne
    Introduction
    Preliminaries
    Z-Order Curves
    Wavelets
    Further Reading

    In Situ Processing, Hank Childs, Kwan-Liu Ma and Hongfeng Yu, Brad Whitlock, Jeremy Meredith, and Jean Favre, Scott Klasky and Norbert Podhorszki, Karsten Schwan and Matthew Wolf, Manish Parashar, and Fan Zhang
    Introduction
    Tailored Co-Processing at High Concurrency
    Co-Processing with General Visualization Tools via Adaptors
    Concurrent Processing
    Service Oriented Architecture for data management in HPC
    In Situ Analytics using Hybrid Staging
    Conclusion

    Streaming and Out-of-Core Methods, David E. DeMarle, Berk Geveci, Jon Woodring, and Jim Ahrens
    External Memory Algorithms
    Taxonomy of Streamed Visualization
    Streamed Visualization Concepts
    Survey of Current State-of-the-Art
    Conclusion

    III Advanced Architectural Challenges and Solutions
    GPU-Accelerated Visualization,
    Marco Ament, Steffen Frey, Christoph Muller, Sebastian Grottel, Thomas Ertl, and Daniel Weiskopf
    Introduction
    Programmable Graphics Hardware
    GPU-Accelerated Volume Rendering
    Particle-Based Rendering
    GPGPU High Performance Environments
    Large Display Visualization

    Hybrid Parallelism, E. Wes Bethel, David Camp, Hank Childs, Chistoph Garth, Mark Howison, Kenneth I. Joy, and Dave Pugmire
    Introduction
    Hybrid Parallelism and Volume Rendering
    Hybrid Parallelism and Integral Curve Calculation
    Conclusion and Future Work

    Visualization at Extreme-Scale Concurrency, Hank Childs, David Pugmire, Sean Ahern, Brad Whitlock, Mark Howison, Prabhat, Gunther Weber, and E. Wes Bethel
    Overview|Pure Parallelism
    Massive Data Experiments
    Scaling Experiments
    Pitfalls at Scale
    Conclusion

    Performance Optimization and Autotuning, E. Wes Bethel and Mark Howison
    Introduction
    Optimizing Performance of a Three-Dimensional Stencil Operator on the GPU
    Optimizing Raycasting Volume Rendering on Multi-Core GPUs and Many-Core GPUs
    Conclusion

    The Path to Exascale, Sean Ahern
    Introduction
    Future System Architectures
    Science Understanding Needs at the Exascale
    Research Directions
    Conclusion and the Path Forward

    IV High Performance Visualization Implementations
    VisIt: An End-User Tool for Visualizing and Analyzing Very Large Data,
    Hank Childs, Eric Brugger, Brad Whitlock, Jeremy Meredith, Sean Ahern, David Pugmire, Kathleen Bonnell, Mark Miller, Cyrus Harrison, Gunther HWeber, Hari Krishnan, Thomas Fogal, Allen Sanderson, Christoph Garth, EWes Bethel, David Camp, Oliver Rubel, Marc Durant, Jean MFavre, and Paul Navrátil
    Introduction
    Focal Points
    Design
    Successes
    Future Challenges
    Conclusion

    IceT, Kenneth Moreland
    Introduction
    Motivation
    Implementation
    Application Programming Interface
    Conclusion

    The ParaView Visualization Application, Utkarsh Ayachit, Berk Geveci, Kenneth Moreland, John Patchett, and Jim Ahrens
    Introduction
    Understanding the Need
    The ParaView Framework
    Parallel Data Processing
    The ParaView Application
    Customizing with Plug-ins and Custom Applications
    Co-processing: In Situ Visualization and Data Analysis
    ParaViewWeb: Interactive Visualization for the Web
    ParaView In Use
    .Conclusion

    The ViSUS Visualization Framework, Valerio Pascucci, Giorgio Scorzelli, Brian Summa, Peer-Timo Bremer, Attila Gyulassy, Cameron Christensen, Sujin Philip, and Sidharth Kumar
    Introduction
    ViSUS Software Architecture
    Applications

    The VAPOR Visualization Application, Alan Norton and John Clyne
    Introduction
    Progressive Data Access
    Visualization-Guided Analysis
    Progressive Access Examination
    Discussion
    Conclusion

    The EnSight Visualization Application, Randall Frank and Michael F. Krogh
    Introduction
    EnSight Architectural Overview
    Cluster Abstraction: CEIShell
    Advanced Rendering
    Conclusion
    Acknowledgments
    Index

    Biography

    E. Wes Bethel, Hank Childs, Charles Hansen

    E. Wes Bethel, Hank Childs, and Chuck Hansen have developed an eminently readable and comprehensive book. It provides the very first in-depth introduction to the interaction of two highly important and relevant topics in computational science: high performance computing and scientific visualization. The book provides a broad background on both topics, but more importantly, for the first time in book form, they describe some of the most recent developments in scientific visualization as we move from the Petascale era to Exaflops computing. … It will provide a solid foundation for anyone who considers using the most recent tools for visualization in order to understand complex simulation data or to understand the ever increasing amount of experimental data. I highly recommend this timely book for scientists and engineers.
    —From the Foreword by Horst Simon, Lawrence Berkeley National Laboratory and University of California, Berkeley