Siggraph 2005 logo
Conference Exhibition Call For Participation Presenters Media Registration

sketches

GPU Programming


Thursday, 4 August
1:45 - 3:30 pm
Room 515A
Session Chair: Dan Wexler, NVIDIA Corporation

Dynamic Adaptive Shadow Maps on Graphics Hardware


A novel implementation of adaptive shadow maps (ASMs) that supports interactive rendering with a moving light and viewpoint. The ASM data structure and refinement algorithm are implemented on the GPU.

Aaron Lefohn
University of California, Davis
lefohn (at) cs.ucdavis.edu

Shubhabrata Sengupta
University of California, Davis

Joe Kniss
University of Utah

Robert Strzodka
Caesar Research Institute

John Owens
University of California, Davis

Building a Graphics Debugger


Implementation Sketch


Building a graphics debugger entails a number of software engineering and algorithmic challenges. This sketch shows which are fundamental to the task and which are simply quirks of today's systems. It discusses the implementation details underlying the SIGGRAPH 2005 Paper: A Relational Debugging Engine for the Graphics Pipeline.

Nathani3l Duca
Johns Hopkins University
duca (at) jhu.edu

Jonathan Cohen
Johns Hopkins University
 

GPU-Accelerated Iterated Function Systems


This sketch describes GPUflame, an application that generates high-quality renderings of iterated function system fractals using GPU hardware to accelerate both the computation and display of the final images.

Simon G. Green
NVIDIA Corporation
sgreen (at) nvidia.com

Octree Textures on Graphics Hardware


An interactive 3D painting application that stores paint in an octree-like GPU-based adaptive data structure. The implementation supports effective resolutions up to 2048x2048x2048 with quadlinear (mipmap) filtering.

Joe Kniss
University of Utah

Aaron Lefohn
University of California, Davis

Robert Strzodka
Caesar Research Institute

Shubhabrata Sengupta
John D. Owens
University of California, Davis
acm.org siggraph.org