DMCA
P.: Ray tracing and volume rendering large molecular data on multi-core and many-core architectures (2013)
| Venue: | In Proceedings of the 8th International Workshop on Ultrascale Visualization |
| Citations: | 3 - 2 self |
BibTeX
@INPROCEEDINGS{Knoll13p.:ray,
author = {Aaron Knoll and Ingo Wald and Paul A. Navrátil and Michael E. Papka and Kelly P. Gaither},
title = {P.: Ray tracing and volume rendering large molecular data on multi-core and many-core architectures},
booktitle = {In Proceedings of the 8th International Workshop on Ultrascale Visualization},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Visualizing large molecular data requires efficient means of ren-dering millions of data elements that combine glyphs, geometry and volumetric techniques. The geometric and volumetric loads challenge traditional rasterization-based vis methods. Ray cast-ing presents a scalable and memory- efficient alternative, but mod-ern techniques typically rely on GPU-based acceleration to achieve interactive rendering rates. In this paper, we present bnsView, a molecular visualization ray tracing framework that delivers fast vol-ume rendering and ball-and-stick ray casting on both multi-core CPUs and many-core Intel R©Xeon PhiTM co-processors, implemented in a SPMD language that generates efficient SIMD vector code for multiple platforms without source modification. We show that our approach running on co- processors is competitive with simi-lar techniques running on GPU accelerators, and we demonstrate large-scale parallel remote visualization from TACC’s Stampede supercomputer to large-format display walls using this system. 1.
Keyphrases
large molecular data ray tracing many-core architecture interactive rendering rate molecular visualization ray efficient simd vector code gpu accelerator multi-core cpu volumetric technique mod-ern technique large-scale parallel remote visualization source modification many-core intel xeon phitm co-processors ray cast-ing present vol-ume rendering traditional rasterization-based vi method ball-and-stick ray casting simi-lar technique gpu-based acceleration efficient mean tacc stampede supercomputer volumetric load ren-dering million co processor spmd language multiple platform data element large-format display wall
