Program

Expected Schedule

Sunday:

11:00 Opening

11:15 In memoriam of Dirk Bartz

11:30-12:30 EGPGV Keynote by Chuck Hansen, Prof. of Computer Science and Associate Director, Scientific Computing and Imaging Institute, University of Utah.

It has been 14 years since the first EGPGV. The graphics and visualization field has seen tremendous change during the past decade and a half. We have moved from superscalar processors to multi-core to many-core as ubiquitous computing platforms. What does this mean for parallel visualization? Has the field been passed by or is it leading others in the pursuit of parallel techniques as applied to science? As we move from the peta-scale range to exa-scale computing, many of the solutions today will no longer be sufficient. This will provide exciting applications for parallel visualization techniques. In this talk I will explore the state of the field and discuss potential benefits and challenges of high-throughput science both from the computational and the experimental perspectives for solving problems in difference science domains from neuroscience to combustion simulations.

13:30-15:00: Volume Rendering

  • MPI-hybrid Parallelism for Volume Rendering on Large, Multi-core Systems
  • Cross Node Occlusion in Sort-Last Volume Rendering
  • Multi-Frame Rate Volume Rendering

15:30-16:30: Ray Tracing

  • Ray Tracing Dynamic Scenes with Shadows on GPU
  • Streamed Ray Tracing of Single Rays on the Cell Processor

Evening: Dinner

Monday:

9:00-10:30 Rendering Techniques

  • Asynchronous Parallel Reliefboard Computation for Scene Object Approximation
  • Parallel View-Dependent Refinement of Compact Progressive Meshes
  • Scalable Parallel Out-of-core Terrain Rendering

11:00-12:30 Isosurface Extraction

  • Self-Scheduled Parallel Isosurfacing using Distributed Span Space on Cell
  • Cache-Efficient Parallel Isosurface Extraction for Shared Cache Multicores
  • Load-Balanced Isosurfacing on Multi-GPU Clusters

13:30-14:30 VG Keynote by Anders Persson, MD PhD, Director at Center for Medical Image Science and Visualization, Linköping University (Volume Graphics website at http://www.eurographics2010.se/vg2010/)

The practice of medical image diagnosis is currently undergoing a fast transformation. Vast amounts of data can be generated in standard examination and focus is shifting from improving the collection of relevant data for diagnosis to development of effective methods to analyze, visualize, navigate, and interact with medical information. It is now becoming generally accepted in the medical community that one of the most important keys to manage the increasing information flow is the use of 3D and 4D applications. This talk will take its starting point in state-of-the-art medical visualization and then discuss the need for a research agenda that focuses on the development of the next generation of medical visualization tools, emphasizing the fact that these tools must be based on medical user requirement and workflow studies as well as on new technical developments.

14:30-15:30 Image Compositing

  • Accelerating and Benchmarking Radix-k Image Compositing at Large Scale
  • Fast Compositing for Cluster-Parallel Rendering

16:00-17:00 Frameworks

  • Towards a Software Transactional Memory for Graphics Processors
  • PaTraCo: A Framework Enabling the Transparent and Efficient Programming
    of Heterogeneous ComputeNetworks

17:00 Closing