Parallel distributed, GPU-accelerated, advanced lighting calculations for large-scale volume visualization
2016 IEEE 6th Symposium on Large Data Analysis and Visualization (LDAV) (2016)
Baltimore, MD, USA
Oct. 23, 2016 to Oct. 28, 2016
Min Shih , University of California, Davis
Silvio Rizzi , Argonne National Laboratory
Joseph Insley , Argonne National Laboratory
Thomas Uram , Argonne National Laboratory
Venkatram Vishwanath , Argonne National Laboratory
Mark Hereld , Argonne National Laboratory
Michael E. Papka , Argonne National Laboratory, Northern Illinois University
Kwan-Liu Ma , University of California, Davis
The benefits of applying advanced illumination models to volume visualization have been demonstrated by many researchers. For a parallel distributed, GPU computing environment, however, there is no efficient algorithm for scalable global illumination calculations. This paper presents a parallel, data-distributed and GPU-accelerated algorithm for volume rendering with advanced lighting. Our approach features tunable soft shadows for enhancing perception of complex spatial structures and relationships. For lighting calculations, our design effectively avoids data exchange among GPUs. Performance evaluation on a GPU cluster using up to 128 GPUs shows scalable rendering performance, with both the number of GPUs and volume data size.
M. Shih et al., "Parallel distributed, GPU-accelerated, advanced lighting calculations for large-scale volume visualization," 2016 IEEE 6th Symposium on Large Data Analysis and Visualization (LDAV), Baltimore, MD, USA, 2016, pp. 47-55.