 | A still from Nano Factor, a game-like toolkit designed to give junior high school students the opportunity to perform virtual experiments based on real-world micro and nano technologies. Image courtesy of Nicoletta Adamo-Villani, Purdue |
Rendering frames in a complex animation can tie up workstations for days or weeks. A two-minute animation at 30 frames per second will typically take over 100 hours to render on a single computer. Sharing the load among hundreds or even thousands of machines dramatically reduces a job’s run time—and the time required to complete a project.
Enter the Distributed Rendering Environment, or DRE, developed at Purdue University five years ago for computer graphics students. It draws on the Purdue Condor pool, a system for sharing unused computing time on more than 20,000 linked processors in computers at Purdue and its partner campuses. This pool is part of both the TeraGrid and the Open Science Grid. DRE has become a staple in the courses from Purdue’s Computer Graphics Technology Department. It allows instructors to present students with more challenging assignments without fear of a bottleneck. The load sharing system lets scientists and animators refine what they're creating almost instantly.
“Now when you press the ‘Render’ button, you have a huge pool of resources out there,” said Gary Bertoline, professor of computer graphics and founding director of Purdue’s Envision Center for Data Perceptualization. After getting it to work well within the partnering campuses, the team wanted to take it to a national level. Recently Purdue revised DRE for TeraGrid use, creating TeraDRE. While DRE runs inside the Purdue system, TeraDRE can run on any TeraGrid resource. | 
Headlines | Site Map
