March 29-30, 2009 - Munich, Germany
 
  Invited Speakers
     
  Peter Shirley, Nvidia

Interactive Ray Tracing: Where Is It Now, and Where Is it Going?

Date: 29th March 2009
Time: TBA

Abstract
Ray tracing has long played a role in batch rendering for applications such as movies, product design, and visualization. It has been a niche tool for interactive visualization on supercomputers. Now that desktop systems are becoming as powerful as previous supercomputers there has been much discussion of whether ray tracing will become a prominent tool for interactive graphics. I will discuss what ray tracing techniques exist now that are useful, as well as trends that will influence ray tracing's future usefulness and adoption. More importantly I will discuss open questions that the research community can address that may determine how and where we may soon see ray tracing in everyday use.

Short Bio

Peter Shirley is a Senior Research Scientist at NVIDIA and Adjunct Professor in the School of Computing at the University of Utah. He has a B.A. in physics from Reed College and a Ph.D. in computer science for the University of Illinois at Urbana-Champaign. He is the coauthor of three books and dozens of technical articles. He spent four years as an Assistant Professor at Indiana University and two years as a Visiting Assistant Professor at the Cornell Program of Computer Graphics before moving to Utah where he was a Professor of Computer Science for twelve years. His professional interests include interactive and realistic rendering, statistical computing, visualization, and immersive environments.


Matt Pharr, Intel

Software Rendering Redux: Back To The Future With New Graphics Architectures

Date: 30th March 2009
Time: 17:00

Abstract
As graphics hardware has become increasingly programmable, we are approaching the point where the entire traditional graphics pipeline can be implemented in software on high-performance general purpose processors. This advance offers great opportunity to graphics researchers and software developers: the standard feed-forward graphics pipeline is no more privileged by the hardware architecture than alternative graphics pipelines, including those based on, for example, direct volume rendering, micropolygon rendering, or ray tracing.

In this talk, I will discuss both the challenges and the opportunities presented by these new architectures. High-performance parallel programming remains a challenge on all graphics architectures today; I will discuss how thoughtful choice of parallel programming models and compilation technology can enable developers to write graphics software that generally executes with very high processor utilization. I will also discuss opportunities in making the standard graphics pipeline highly extensible, allowing developers to leverage existing highly-tuned software graphics pipelines to implement new rendering algorithms rather than needing to write complete graphics pipelines themselves from scratch.

Short Bio
Matt Pharr is the lead graphics architect in the Advanced Rendering Technology group at Intel, working on interactive rendering for Larrabee. He previously co-founded Neoptica, which worked on programming models for graphics on heterogeneous CPU+GPU systems; Neoptica was acquired by Intel. Before Neoptica, Matt was in the Software Architecture group at NVIDIA, co-founded Exluna, worked in Pixar's Rendering R&D group, and received his PhD from the Stanford Graphics Lab. With Greg Humphreys, he wrote the textbook "Physically Based Rendering: From Theory to Implementation". He was also the editor of "GPU Gems 2" and the winner of the first Fantasy Graphics League.