Abstract
In order to achieve higher rendering performance, the use of parallel sort-last architecture on a PC cluster is presented. The sort-last library (libpglc) can be linked to an existing parallel application to achieve high rendering rates. The efficient use of 64 commodity graphics cards enables to establish pace-setting rendering performance of 300 million triangles per second on extremely large data.
| Original language | English |
|---|---|
| Pages (from-to) | 62-70 |
| Number of pages | 9 |
| Journal | IEEE Computer Graphics and Applications |
| Volume | 21 |
| Issue number | 4 |
| DOIs | |
| State | Published - Jul 2001 |
| Externally published | Yes |
Funding
Funding was provided by the Accelerated Strategic Computing Initiative’s Visual Interactive Environment for Weapons Simulations (ASCI/Views) program. Thanks to Milt Clauser and Steve Monk for their work on the visualization and data manipulation clusters. Thanks to LLNL for the large isosurface data (particularly Randy Frank and Dan Schikore, now with CEI). Thanks to Pat Crossno for her vast technical library and extremely helpful suggestions, Dan Zimmerer for his research and development on cluster support, Phil Heermann for his inspiration and motivation, and Lisa Ice for her work on ParallelMesa (PMesa). The US Department of Energy supported this work under contract DE-AC04-94AL85000.
| Funders | Funder number |
|---|---|
| US Department of Energy | DE-AC04-94AL85000 |